Search

Accurate assessment of personality traits is crucial for effective psycho-counseling, yet traditional methods like self-report questionnaires are time-consuming and biased. This study exams whether Large Language Models (LLMs) can predict the Big Five personality traits directly from counseling dialogues and introduces an innovative framework to perform the task. Our framework applies role-play and questionnaire-based prompting to condition LLMs on counseling sessions, simulating client responses to the Big Five Inventory. We evaluated our framework on 853 real-world counseling sessions, finding a significant correlation between LLM-predicted and actual Big Five traits, proving the validity of framework. Moreover, ablation studies highlight the importance of role-play simulations and task simplification via questionnaires in enhancing prediction accuracy. Meanwhile, our fine-tuned Llama3-8B model, utilizing Direct Preference Optimization with Supervised Fine-Tuning, achieves a 130.95\% improvement, surpassing the state-of-the-art Qwen1.5-110B by 36.94\% in personality prediction validity. In conclusion, LLMs can predict personality based on counseling dialogues. Our code and model are publicly available at \url{https://github.com/kuri-leo/BigFive-LLM-Predictor}, providing a valuable tool for future research in computational psychometrics.

Although recent generative image compression methods have demonstrated impressive potential in optimizing the rate-distortion-perception trade-off, they still face the critical challenge of flexible rate adaption to diverse compression necessities and scenarios. To overcome this challenge, this paper proposes a Controllable Generative Image Compression framework, Control-GIC, the first capable of fine-grained bitrate adaption across a broad spectrum while ensuring high-fidelity and generality compression. We base Control-GIC on a VQGAN framework representing an image as a sequence of variable-length codes (i.e. VQ-indices), which can be losslessly compressed and exhibits a direct positive correlation with the bitrates. Therefore, drawing inspiration from the classical coding principle, we naturally correlate the information density of local image patches with their granular representations, to achieve dynamic adjustment of the code quantity following different granularity decisions. This implies we can flexibly determine a proper allocation of granularity for the patches to acquire desirable compression rates. We further develop a probabilistic conditional decoder that can trace back to historic encoded multi-granularity representations according to transmitted codes, and then reconstruct hierarchical granular features in the formalization of conditional probability, enabling more informative aggregation to improve reconstruction realism. Our experiments show that Control-GIC allows highly flexible and controllable bitrate adaption and even once compression on an entire dataset to fulfill constrained bitrate conditions. Experimental results demonstrate its superior performance over recent state-of-the-art methods.

A system of linear equations $L$ is common over $\mathbb{F}_p$ if, as $n\to\infty$, any 2-coloring of $\mathbb{F}_p^n$ gives asymptotically at least as many monochromatic solutions to $L$ as a random 2-coloring. The notion of common linear systems is analogous to that of common graphs, i.e., graphs whose monochromatic density in 2-edge-coloring of cliques is asymptotically minimized by the random coloring. Saad and Wolf initiated a systematic study on identifying common linear systems, built upon the earlier work of Cameron-Cilleruelo-Serra. When $L$ is a single equation, Fox-Pham-Zhao gave a complete characterization of common linear equations. When $L$ consists of two equations, Kam\v{c}ev-Liebenau-Morrison showed that irredundant $2\times 4$ linear systems are always uncommon. In this work, (1) we determine commonness of all $2\times 5$ linear systems up to a small number of cases, and (2) we show that all $2\times k$ linear systems with $k$ even and girth (minimum number of nonzero coefficients of a nonzero equation spanned by the system) $k-1$ are uncommon, answering a question of Kam\v{c}ev-Liebenau-Morrison., Comment: 59 pages, 1 figure

Traffic flow prediction is an essential task in constructing smart cities and is a typical Multivariate Time Series (MTS) Problem. Recent research has abandoned Gated Recurrent Units (GRU) and utilized dilated convolutions or temporal slicing for feature extraction, and they have the following drawbacks: (1) Dilated convolutions fail to capture the features of adjacent time steps, resulting in the loss of crucial transitional data. (2) The connections within the same temporal slice are strong, while the connections between different temporal slices are too loose. In light of these limitations, we emphasize the importance of analyzing a complete time series repeatedly and the crucial role of GRU in MTS. Therefore, we propose SGRU: Structured Gated Recurrent Units, which involve structured GRU layers and non-linear units, along with multiple layers of time embedding to enhance the model's fitting performance. We evaluate our approach on four publicly available California traffic datasets: PeMS03, PeMS04, PeMS07, and PeMS08 for regression prediction. Experimental results demonstrate that our model outperforms baseline models with average improvements of 11.7%, 18.6%, 18.5%, and 12.0% respectively., Comment: 7 pages, 6 figures, conference

We introduce and study the problem of posterior inference on tree-structured graphical models in the presence of a malicious adversary who can corrupt some observed nodes. In the well-studied broadcasting on trees model, corresponding to the ferromagnetic Ising model on a $d$-regular tree with zero external field, when a natural signal-to-noise ratio exceeds one (the celebrated Kesten-Stigum threshold), the posterior distribution of the root given the leaves is bounded away from $\mathrm{Ber}(1/2)$, and carries nontrivial information about the sign of the root. This posterior distribution can be computed exactly via dynamic programming, also known as belief propagation. We first confirm a folklore belief that a malicious adversary who can corrupt an inverse-polynomial fraction of the leaves of their choosing makes this inference impossible. Our main result is that accurate posterior inference about the root vertex given the leaves is possible when the adversary is constrained to make corruptions at a $\rho$-fraction of randomly-chosen leaf vertices, so long as the signal-to-noise ratio exceeds $O(\log d)$ and $\rho \leq c \varepsilon$ for some universal $c > 0$. Since inference becomes information-theoretically impossible when $\rho \gg \varepsilon$, this amounts to an information-theoretically optimal fraction of corruptions, up to a constant multiplicative factor. Furthermore, we show that the canonical belief propagation algorithm performs this inference.

Pornographic content occurring in human-machine interaction dialogues can cause severe side effects for users in open-domain dialogue systems. However, research on detecting pornographic language within human-machine interaction dialogues is an important subject that is rarely studied. To advance in this direction, we introduce CensorChat, a dialogue monitoring dataset aimed at detecting whether the dialogue session contains pornographic content. To this end, we collect real-life human-machine interaction dialogues in the wild and break them down into single utterances and single-turn dialogues, with the last utterance spoken by the chatbot. We propose utilizing knowledge distillation of large language models to annotate the dataset. Specifically, first, the raw dataset is annotated by four open-source large language models, with the majority vote determining the label. Second, we use ChatGPT to update the empty label from the first step. Third, to ensure the quality of the validation and test sets, we utilize GPT-4 for label calibration. If the current label does not match the one generated by GPT-4, we employ a self-criticism strategy to verify its correctness. Finally, to facilitate the detection of pornographic text, we develop a series of text classifiers using a pseudo-labeled dataset. Detailed data analysis demonstrates that leveraging knowledge distillation techniques with large language models provides a practical and cost-efficient method for developing pornographic text detectors., Comment: Accepted to CSCWD 2024 (27th International Conference on Computer Supported Cooperative Work in Design). arXiv admin note: text overlap with arXiv:2309.09749

High-quality psychological counseling is crucial for mental health worldwide, and timely evaluation is vital for ensuring its effectiveness. However, obtaining professional evaluation for each counseling session is expensive and challenging. Existing methods that rely on self or third-party manual reports to assess the quality of counseling suffer from subjective biases and limitations of time-consuming. To address above challenges, this paper proposes an innovative and efficient automatic approach using large language models (LLMs) to evaluate the working alliance in counseling conversations. We collected a comprehensive counseling dataset and conducted multiple third-party evaluations based on therapeutic relationship theory. Our LLM-based evaluation, combined with our guidelines, shows high agreement with human evaluations and provides valuable insights into counseling scripts. This highlights the potential of LLMs as supervisory tools for psychotherapists. By integrating LLMs into the evaluation process, our approach offers a cost-effective and dependable means of assessing counseling quality, enhancing overall effectiveness., Comment: 21 pages, 4 figures

We study the applicability of the Liouvillian exceptional points (LEPs) approach to nanoscale open quantum systems. A generic model of the driven two-level system in a thermal environment is analyzed within the nonequilibrium Green's function (NEGF) and Bloch quantum master equation (QME) formulations. We derive the latter starting from the exact NEGF Dyson equations and highlight the qualitative limitations of the LEP treatment by examining the approximations employed in its derivation. We find that non-Markov character of evolution in open quantum systems does not allow for the introduction of the concept of exceptional points for a description of their dynamics. Theoretical analysis is illustrated with numerical simulations., Comment: 11 pages, 4 figures

Existing methods provide varying algorithms for different types of Boolean satisfiability problems (SAT), lacking a general solution framework. Accordingly, this study proposes a unified framework DCSAT based on integer programming and reinforcement learning (RL) algorithm to solve different types of SAT problems such as MaxSAT, Weighted MaxSAT, PMS, WPMS. Specifically, we first construct a consolidated integer programming representation for four types of SAT problems by adjusting objective function coefficients. Secondly, we construct an appropriate reinforcement learning models based on the 0-1 integer programming for SAT problems. Based on the binary tree search structure, we apply the Monte Carlo tree search (MCTS) method on SAT problems. Finally, we prove that this method can find all optimal Boolean assignments based on Wiener-khinchin law of large Numbers. We experimentally verify that this paradigm can prune the unnecessary search space to find the optimal Boolean assignments for the problem. Furthermore, the proposed method can provide diverse labels for supervised learning methods for SAT problems., Comment: 34 pages

Dialogue systems are increasingly integrated into mental health support to help clients facilitate exploration, gain insight, take action, and ultimately heal themselves. A practical and user-friendly dialogue system should be client-centric, focusing on the client's behaviors. However, existing dialogue systems publicly available for mental health support often concentrate solely on the counselor's strategies rather than the behaviors expressed by clients. This can lead to unreasonable or inappropriate counseling strategies and corresponding responses generated by the dialogue system. To address this issue, we propose PsyChat, a client-centric dialogue system that provides psychological support through online chat. The client-centric dialogue system comprises five modules: client behavior recognition, counselor strategy selection, input packer, response generator, and response selection. Both automatic and human evaluations demonstrate the effectiveness and practicality of our proposed dialogue system for real-life mental health support. Furthermore, the case study demonstrates that the dialogue system can predict the client's behaviors, select appropriate counselor strategies, and generate accurate and suitable responses., Comment: Accepted to CSCWD 2024 (27th International Conference on Computer Supported Cooperative Work in Design)

Terrain traversability in unstructured off-road autonomy has traditionally relied on semantic classification, resource-intensive dynamics models, or purely geometry-based methods to predict vehicle-terrain interactions. While inconsequential at low speeds, uneven terrain subjects our full-scale system to safety-critical challenges at operating speeds of 7--10 m/s. This study focuses particularly on uneven terrain such as hills, banks, and ditches. These common high-risk geometries are capable of disabling the vehicle and causing severe passenger injuries if poorly traversed. We introduce a physics-based framework for identifying traversability constraints on terrain dynamics. Using this framework, we derive two fundamental constraints, each with a focus on mitigating rollover and ditch-crossing failures while being fully parallelizable in the sample-based Model Predictive Control (MPC) framework. In addition, we present the design of our planning and control system, which implements our parallelized constraints in MPC and utilizes a low-level controller to meet the demands of our aggressive driving without prior information about the environment and its dynamics. Through real-world experimentation and traversal of hills and ditches, we demonstrate that our approach captures fundamental elements of safe and aggressive autonomy over uneven terrain. Our approach improves upon geometry-based methods by completing comprehensive off-road courses up to 22% faster while maintaining safe operation., Comment: Accepted to R:SS 2024

The critical field of psychology necessitates a comprehensive benchmark to enhance the evaluation and development of domain-specific Large Language Models (LLMs). Existing MMLU-type benchmarks, such as C-EVAL and CMMLU, include psychology-related subjects, but their limited number of questions and lack of systematic concept sampling strategies mean they cannot cover the concepts required in psychology. Consequently, despite their broad subject coverage, these benchmarks lack the necessary depth in the psychology domain, making them inadequate as psychology-specific evaluation suite. To address this issue, this paper presents ConceptPsy, designed to evaluate Chinese complex reasoning and knowledge abilities in psychology. ConceptPsy includes 12 core subjects and 1383 manually collected concepts. Specifically, we prompt GPT-4 to generate questions for each concept using carefully designed diverse prompts and hire professional psychologists to review these questions. To help to understand the fine-grained performances and enhance the weaknesses, we annotate each question with a chapter label and provide chapter-wise accuracy. Based on ConceptPsy, we evaluate a broad range of LLMs. We observe that, although some LLMs achieve similar accuracies on overall performances, they exhibit significant performance variations across different psychology concepts, even when they are models from the same series. We hope our work can facilitate the development of LLMs in the field of psychology., Comment: Under Review

NSFW (Not Safe for Work) content, in the context of a dialogue, can have severe side effects on users in open-domain dialogue systems. However, research on detecting NSFW language, especially sexually explicit content, within a dialogue context has significantly lagged behind. To address this issue, we introduce CensorChat, a dialogue monitoring dataset aimed at NSFW dialogue detection. Leveraging knowledge distillation techniques involving GPT-4 and ChatGPT, this dataset offers a cost-effective means of constructing NSFW content detectors. The process entails collecting real-life human-machine interaction data and breaking it down into single utterances and single-turn dialogues, with the chatbot delivering the final utterance. ChatGPT is employed to annotate unlabeled data, serving as a training set. Rationale validation and test sets are constructed using ChatGPT and GPT-4 as annotators, with a self-criticism strategy for resolving discrepancies in labeling. A BERT model is fine-tuned as a text classifier on pseudo-labeled data, and its performance is assessed. The study emphasizes the importance of AI systems prioritizing user safety and well-being in digital conversations while respecting freedom of expression. The proposed approach not only advances NSFW content detection but also aligns with evolving user protection needs in AI-driven dialogues., Comment: As we have submitted a final version arXiv:2403.13250, we decide to withdraw it

We study how a decision maker (DM) learns about the biases of unfamiliar information sources. Absent any friction, a rational DM uses familiar sources as yardsticks to discern the true bias of a source. If the DM has misspecified beliefs, this process fails. We derive long-run beliefs, behavior, welfare, and corresponding comparative statics when the DM holds dogmatic, incorrect beliefs about the biases of several familiar sources. The distortion due to misspecified learning aggregates misspecifications associated with familiar sources independently of sources the DM learns about. This has implications for labor market discrimination, media bias, and project finance and oversight.

We introduce an energy-resolved variant of quantum thermodynamics for open systems strongly coupled to their baths. The approach generalizes the Landauer-Buttiker inside-outside duality method [Phys. Rev. Lett. 120, 107701 (2018)] to interacting systems subjected to arbitrary external driving. It is consistent with the underlying dynamical quantum transport description and is capable of overcoming limitations of the only other consistent approach [New J. Phys. 12, 013013 (2010)]. We illustrate viability of the generalized inside-outside method with numerical simulations for generic junction models., Comment: 11 pages, 3 figures

Dialogue safety remains a pervasive challenge in open-domain human-machine interaction. Existing approaches propose distinctive dialogue safety taxonomies and datasets for detecting explicitly harmful responses. However, these taxonomies may not be suitable for analyzing response safety in mental health support. In real-world interactions, a model response deemed acceptable in casual conversations might have a negligible positive impact on users seeking mental health support. To address these limitations, this paper aims to develop a theoretically and factually grounded taxonomy that prioritizes the positive impact on help-seekers. Additionally, we create a benchmark corpus with fine-grained labels for each dialogue session to facilitate further research. We analyze the dataset using popular language models, including BERT-base, RoBERTa-large, and ChatGPT, to detect and understand unsafe responses within the context of mental health support. Our study reveals that ChatGPT struggles to detect safety categories with detailed safety definitions in a zero- and few-shot paradigm, whereas the fine-tuned model proves to be more suitable. The developed dataset and findings serve as valuable benchmarks for advancing research on dialogue safety in mental health support, with significant implications for improving the design and deployment of conversation agents in real-world applications. We release our code and data here: https://github.com/qiuhuachuan/DialogueSafety., Comment: accepted to The 12th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC2023)

Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks mainly focus on measuring models' accuracy using multi-choice questions, which limits the understanding of their capabilities in real applications. We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE. SuperCLUE encompasses three sub-tasks: actual users' queries and ratings derived from an LLM battle platform (CArena), open-ended questions with single and multiple-turn dialogues (OPEN), and closed-ended questions with the same stems as open-ended single-turn ones (CLOSE). Our study shows that accuracy on closed-ended questions is insufficient to reflect human preferences achieved on open-ended ones. At the same time, they can complement each other to predict actual user preferences. We also demonstrate that GPT-4 is a reliable judge to automatically evaluate human preferences on open-ended questions in a Chinese context. Our benchmark will be released at https://www.CLUEbenchmarks.com, Comment: 13 pages, 12 figures, 5 tables

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness in following instructions, thereby impacting its overall performance in completing tasks. Previous benchmarks for jailbreaking LLMs have primarily focused on evaluating the safety of the models without considering their robustness. In this paper, we propose a benchmark that assesses both the safety and robustness of LLMs, emphasizing the need for a balanced approach. To comprehensively study text safety and output robustness, we introduce a latent jailbreak prompt dataset, each involving malicious instruction embedding. Specifically, we instruct the model to complete a regular task, such as translation, with the text to be translated containing malicious instructions. To further analyze safety and robustness, we design a hierarchical annotation framework. We present a systematic analysis of the safety and robustness of LLMs regarding the position of explicit normal instructions, word replacements (verbs in explicit normal instructions, target groups in malicious instructions, cue words for explicit normal instructions), and instruction replacements (different explicit normal instructions). Our results demonstrate that current LLMs not only prioritize certain instruction verbs but also exhibit varying jailbreak rates for different instruction verbs in explicit normal instructions. Code and data are available at https://github.com/qiuhuachuan/latent-jailbreak., Comment: Code and data are available at https://github.com/qiuhuachuan/latent-jailbreak

Learned image compression (LIC) methods have experienced significant progress during recent years. However, these methods are primarily dedicated to optimizing the rate-distortion (R-D) performance at medium and high bitrates (> 0.1 bits per pixel (bpp)), while research on extremely low bitrates is limited. Besides, existing methods fail to explicitly explore the image structure and texture components crucial for image compression, treating them equally alongside uninformative components in networks. This can cause severe perceptual quality degradation, especially under low-bitrate scenarios. In this work, inspired by the success of pre-trained masked autoencoders (MAE) in many downstream tasks, we propose to rethink its mask sampling strategy from structure and texture perspectives for high redundancy reduction and discriminative feature representation, further unleashing the potential of LIC methods. Therefore, we present a dual-adaptive masking approach (DA-Mask) that samples visible patches based on the structure and texture distributions of original images. We combine DA-Mask and pre-trained MAE in masked image modeling (MIM) as an initial compressor that abstracts informative semantic context and texture representations. Such a pipeline can well cooperate with LIC networks to achieve further secondary compression while preserving promising reconstruction quality. Consequently, we propose a simple yet effective masked compression model (MCM), the first framework that unifies MIM and LIC end-to-end for extremely low-bitrate image compression. Extensive experiments have demonstrated that our approach outperforms recent state-of-the-art methods in R-D performance, visual quality, and downstream applications, at very low bitrates. Our code is available at https://github.com/lianqi1008/MCM.git., Comment: Under review

Communication success relies heavily on reading participants' reactions. Such feedback is especially important for mental health counselors, who must carefully consider the client's progress and adjust their approach accordingly. However, previous NLP research on counseling has mainly focused on studying counselors' intervention strategies rather than their clients' reactions to the intervention. This work aims to fill this gap by developing a theoretically grounded annotation framework that encompasses counselors' strategies and client reaction behaviors. The framework has been tested against a large-scale, high-quality text-based counseling dataset we collected over the past two years from an online welfare counseling platform. Our study shows how clients react to counselors' strategies, how such reactions affect the final counseling outcomes, and how counselors can adjust their strategies in response to these reactions. We also demonstrate that this study can help counselors automatically predict their clients' states., Comment: Accept to ACL 2023, oral. For code and data, see https://github.com/dll-wu/Client-React

We present a novel observation about the behavior of offline reinforcement learning (RL) algorithms: on many benchmark datasets, offline RL can produce well-performing and safe policies even when trained with "wrong" reward labels, such as those that are zero everywhere or are negatives of the true rewards. This phenomenon cannot be easily explained by offline RL's return maximization objective. Moreover, it gives offline RL a degree of robustness that is uncharacteristic of its online RL counterparts, which are known to be sensitive to reward design. We demonstrate that this surprising robustness property is attributable to an interplay between the notion of pessimism in offline RL algorithms and certain implicit biases in common data collection practices. As we prove in this work, pessimism endows the agent with a "survival instinct", i.e., an incentive to stay within the data support in the long term, while the limited and biased data coverage further constrains the set of survival policies. Formally, given a reward class -- which may not even contain the true reward -- we identify conditions on the training data distribution that enable offline RL to learn a near-optimal and safe policy from any reward within the class. We argue that the survival instinct should be taken into account when interpreting results from existing offline RL benchmarks and when creating future ones. Our empirical and theoretical results suggest a new paradigm for RL, whereby an agent is nudged to learn a desirable behavior with imperfect reward but purposely biased data coverage.

NICE-SLAM is a dense visual SLAM system that combines the advantages of neural implicit representations and hierarchical grid-based scene representation. However, the hierarchical grid features are densely stored, leading to memory explosion problems when adapting the framework to large scenes. In our project, we present sparse NICE-SLAM, a sparse SLAM system incorporating the idea of Voxel Hashing into NICE-SLAM framework. Instead of initializing feature grids in the whole space, voxel features near the surface are adaptively added and optimized. Experiments demonstrated that compared to NICE-SLAM algorithm, our approach takes much less memory and achieves comparable reconstruction quality on the same datasets. Our implementation is available at https://github.com/zhangganlin/NICE-SLAM-with-Adaptive-Feature-Grids., Comment: This is a course project, not suitable for a preprint platform

Developing specialized dialogue systems for mental health support requires multi-turn conversation data, which has recently garnered increasing attention. However, gathering and releasing large-scale and real-life multi-turn conversations to facilitate advancements in mental health presents challenges due to data privacy protection, as well as the time and cost involved. To address the challenges related to data scarcity, we introduce SMILE, a single-turn to multi-turn inclusive language expansion technique that prompts ChatGPT to rewrite public single-turn dialogues into multi-turn ones. Our work begins with the analysis of language transformation, validating the feasibility of the proposed method when compared with other baseline methods. We then conduct a study on dialogue diversity, including lexical features, semantic features, and dialogue topics, demonstrating the effectiveness of our proposed method. Furthermore, we implement an expert evaluation and the results demonstrate that the dialogues generated with our proposed method are of higher quality than those generated with other baseline methods. Thus, we employ our method to generate a large-scale, diverse, and high-quality dialogue dataset named SmileChat, comprising 55,165 dialogues in total with an average of 10.4 turns per dialogue. Finally, we utilize the collected corpus to develop a mental health chatbot, MeChat. To better assess the overall quality of SmileChat, we collect a real-life chat dataset comprising 82 counseling dialogues for model evaluation. Both automatic and human evaluations demonstrate that our trained dialogue system exhibits significant improvements, showcasing that SmileChat is high-quality and practical., Comment: 22 pages

The infrared response of a system of two vibrational modes in a cavity is calculated by an effective non-Hermitian Hamiltonian derived by employing the nonequilibrium Green's functions (NEGF) formalism. Degeneracies of the Hamiltonian (exceptional points, EP) widely employed in theoretical analysis of optical cavity spectroscopies are used in an approximate treatment and compared with the full NEGF. Qualitative limitations of the EP treatment are explained by examining the approximations employed in the calculation., Comment: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in J. Chem. Phys. 158, 154106 (2023) and may be found at https://doi.org/10.1063/5.0142022 Copyright (2023) Authors. This article is distributed under a Creative Commons Attribution (CC BY) License

We study a new paradigm for sequential decision making, called offline policy learning from observations (PLfO). Offline PLfO aims to learn policies using datasets with substandard qualities: 1) only a subset of trajectories is labeled with rewards, 2) labeled trajectories may not contain actions, 3) labeled trajectories may not be of high quality, and 4) the data may not have full coverage. Such imperfection is common in real-world learning scenarios, and offline PLfO encompasses many existing offline learning setups, including offline imitation learning (IL), offline IL from observations (ILfO), and offline reinforcement learning (RL). In this work, we present a generic approach to offline PLfO, called $\textbf{M}$odality-agnostic $\textbf{A}$dversarial $\textbf{H}$ypothesis $\textbf{A}$daptation for $\textbf{L}$earning from $\textbf{O}$bservations (MAHALO). Built upon the pessimism concept in offline RL, MAHALO optimizes the policy using a performance lower bound that accounts for uncertainty due to the dataset's insufficient coverage. We implement this idea by adversarially training data-consistent critic and reward functions, which forces the learned policy to be robust to data deficiency. We show that MAHALO consistently outperforms or matches specialized algorithms across a variety of offline PLfO tasks in theory and experiments. Our code is available at https://github.com/AnqiLi/mahalo.

Effective use of camera-based vision systems is essential for robust performance in autonomous off-road driving, particularly in the high-speed regime. Despite success in structured, on-road settings, current end-to-end approaches for scene prediction have yet to be successfully adapted for complex outdoor terrain. To this end, we present TerrainNet, a vision-based terrain perception system for semantic and geometric terrain prediction for aggressive, off-road navigation. The approach relies on several key insights and practical considerations for achieving reliable terrain modeling. The network includes a multi-headed output representation to capture fine- and coarse-grained terrain features necessary for estimating traversability. Accurate depth estimation is achieved using self-supervised depth completion with multi-view RGB and stereo inputs. Requirements for real-time performance and fast inference speeds are met using efficient, learned image feature projections. Furthermore, the model is trained on a large-scale, real-world off-road dataset collected across a variety of diverse outdoor environments. We show how TerrainNet can also be used for costmap prediction and provide a detailed framework for integration into a planning module. We demonstrate the performance of TerrainNet through extensive comparison to current state-of-the-art baselines for camera-only scene prediction. Finally, we showcase the effectiveness of integrating TerrainNet within a complete autonomous-driving stack by conducting a real-world vehicle test in a challenging off-road scenario.

We use a dynamical model of galactic fountain to study the neutral extraplanar gas (EPG) in the nearby spiral galaxy NGC 2403. We have modelled the EPG as a combination of material ejected from the disc by stellar feedback (i.e. galactic fountain) and gas accreting from the inner circumgalactic medium (CGM). This accretion is expected to occur because of cooling/condensation of the hot CGM (corona) triggered by the fountain. Our dynamical model reproduces the distribution and kinematics of the EPG H$\mathrm{\scriptsize{I}}$ emission in NGC 2403 remarkably well and suggests a total EPG mass of $4.7^{+1.2}_{-0.9}\times10^8\mathrm{M}_\odot$, with a typical scale height of around 1 kpc and a vertical gradient of the rotation velocity of $-10.0\pm2.7\,\mathrm{km\,s^{-1}\,kpc^{-1}}$. The best-fitting model requires a characteristic outflow velocity of $50\pm10\,\mathrm{km\,s^{-1}}$. The outflowing gas starts out mostly ionised and only becomes neutral later in the trajectory. The accretion rate from the condensation of the inner hot CGM inferred by the model is 0.8$\,\mathrm{M}_\odot\,\mathrm{yr}^{-1}$, approximately equal to the star formation rate in this galaxy (0.6$\,\mathrm{M}_\odot\,\mathrm{yr}^{-1}$). We show that the accretion profile, which peaks at a radius of about 4.5$\,$kpc, predicts a disc growth rate compatible with the observed value. Our results indicate that fountain-driven corona condensation is a likely mechanism to sustain star formation as well as the disc inside-out growth in local disc galaxies., Comment: 15 pages, 9 figures, accepted for publication in MNRAS

Mapping crops using remote sensing technology is important for food security and land management. Machine learning-based methods has become a popular approach for crop mapping in recent years. However, the key to machine learning, acquiring ample and accurate samples, is usually time-consuming and laborious. To solve this problem, a crop mapping method in the small sample/no sample case that integrating domain knowledge and using a cascaded classification framework that combine a weak classifier learned from samples with strong features and a strong classifier trained by samples with weak feature was proposed. First, based on the domain knowledge of various crops, a low-capacity classifier such as decision tree was applied to acquire those pixels with distinctive features and complete observation sequences as "strong feature" samples. Then, to improve the representativeness of these samples, sample augmentation strategy that artificially remove the observations of "strong feature" samples according to the average valid observation proportion in target area was applied. Finally, based on the original samples and augmented samples, a large-capacity classifier such as random forest was trained for crop mapping. The method achieved an overall accuracy of 82% in the MAP crop recognition competition held by Syngenta Group, China in 2021 (third prize, ranked fourth). This method integrates domain knowledge to overcome the difficulties of sample acquisition, providing a convenient, fast and accurate solution for crop mapping., Comment: in Chinese language

In this paper, we strengthen a result by Green about an analogue of Sarkozy's theorem in the setting of polynomial rings $\mathbb{F}_q[x]$. In the integer setting, for a given polynomial $F \in \mathbb{Z}[x]$ with constant term zero, (a generalization of) Sarkozy's theorem gives an upper bound on the maximum size of a subset $A \subset \{1, \ldots, n \}$ that does not contain distinct $a_1,a_2 \in A$ satisfying $a_1 - a_2 = F(b)$ for some $ b \in \mathbb{Z}$. Green proved an analogous result with much stronger bounds in the setting of subsets $A \subset \mathbb{F}_q[x]$ of the polynomial ring $\mathbb{F}_q[x]$, but required the additional condition that the number of roots of the polynomial $F \in \mathbb{F}_q[x]$ is coprime to $q$. We generalize Green's result, removing this condition. As an application, we also obtain a version of Sarkozy's theorem with similarly strong bounds for subsets $A \subset \mathbb{F}_q$ for $q = p^n$ for a fixed prime $p$ and large $n$.

When information acquisition is costly but flexible, a principal may rationally acquire information that favors "majorities" over "minorities." Majorities therefore face incentives to invest in becoming productive, whereas minorities are discouraged from such investments. The principal, in turn, rationally ignores minorities unless they surprise him with a genuinely outstanding outcome, precisely because they are less likely to invest. We give conditions under which the resulting discriminatory equilibrium is most preferred by the principal, despite that all groups are ex-ante identical. Our results add to the discussions of affirmative action, implicit bias, and occupational segregation and stereotypes.

Instances generation is crucial for linear programming algorithms, which is necessary either to find the optimal pivot rules by training learning method or to evaluate and verify corresponding algorithms. This study proposes a general framework for designing linear programming instances based on the preset optimal solution. First, we give a constraint matrix generation method with controllable condition number and rank from the perspective of matrix decomposition. Based on the preset optimal solution, the bounded feasible linear programming instance is generated with the right-hand side and objective coefficient satisfying the original and dual feasibility. In addition, we provide three kind of neighborhood exchange operators and prove that instances generated under this method can fill the whole feasible and bounded case space of linear programming. We experimentally validate that the proposed schedule can generate more controllable linear programming instances, while neighborhood exchange operator can construct more complex instances., Comment: 28 pages

Based on the existing pivot rules, the simplex method for linear programming is not polynomial in the worst case. Therefore the optimal pivot of the simplex method is crucial. This study proposes the optimal rule to find all shortest pivot paths of the simplex method for linear programming problems based on Monte Carlo tree search (MCTS). Specifically, we first propose the SimplexPseudoTree to transfer the simplex method into tree search mode while avoiding repeated basis variables. Secondly, we propose four reinforcement learning (RL) models with two actions and two rewards to make the Monte Carlo tree search suitable for the simplex method. Thirdly, we set a new action selection criterion to ameliorate the inaccurate evaluation in the initial exploration. It is proved that when the number of vertices in the feasible region is $C_n^m$, our method can generate all the shortest pivot paths, which is the polynomial of the number of variables. In addition, we experimentally validate that the proposed schedule can avoid unnecessary search and provide the optimal pivot path. Furthermore, this method can provide the best pivot labels for all kinds of supervised learning methods to solve linear programming problems., Comment: 38 pages

For a finite irreducible Coxeter group $(W,S)$ with a fixed Coxeter element $c$ and set of reflections $T$, Defant and Williams define a pop-tsack torsing operation $\mathrm{Popt}\colon W \to W$ given by $\mathrm{Popt}(w) = w \cdot \pi_T(w)^{-1}$ where $\pi_T(w) = \bigvee_{t \leq_{T}w, \ t \in T}^{NC(w,c)}t$ is the join of all reflections lying below $w$ in the absolute order in the non-crossing partition lattice $NC(w,c)$. This is a "dual" notion of the pop-stack sorting operator $\mathrm{Pops}$ introduced by Defant as a way to generalize the pop-stack sorting operator on $\mathfrak{S}_n$ to general Coxeter groups. Define the forward orbit of an element $w \in W$ to be $O_{\mathrm{Popt}}(w) = \{w, \mathrm{Popt}(w), \mathrm{Popt}^2(w), \ldots \}$. Defant and Williams established the length of the longest possible forward orbits $\max_{w \in W}|O_{\mathrm{Popt}}(w)|$ for Coxeter groups of coincidental types and type $D$ in terms of the corresponding Coxeter number of the group. In their paper, they also proposed multiple conjectures about enumerating elements with near maximal orbit length. We resolve all the conjectures that they have put forth about enumeration, and in the process we give complete classifications of these elements of Coxeter groups of types $A,B$ and $D$ with near maximal orbit lengths., Comment: 26 pages, 19 figures. arXiv admin note: text overlap with arXiv:2106.05471 by other authors

In this paper, we give a cubic Goldreich-Levin algorithm which makes polynomially-many queries to a function $f \colon \mathbb F_p^n \to \mathbb C$ and produces a decomposition of $f$ as a sum of cubic phases and a small error term. This is a natural higher-order generalization of the classical Goldreich-Levin algorithm. The classical (linear) Goldreich-Levin algorithm has wide-ranging applications in learning theory, coding theory and the construction of pseudorandom generators in cryptography, as well as being closely related to Fourier analysis. Higher-order Goldreich-Levin algorithms on the other hand involve central problems in higher-order Fourier analysis, namely the inverse theory of the Gowers $U^k$ norms, which are well-studied in additive combinatorics. The only known result in this direction prior to this work is the quadratic Goldreich-Levin theorem, proved by Tulsiani and Wolf in 2011. The main step of their result involves an algorithmic version of the $U^3$ inverse theorem. More complications appear in the inverse theory of the $U^4$ and higher norms. Our cubic Goldreich-Levin algorithm is based on algorithmizing recent work by Gowers and Mili\'cevi\'c who proved new quantitative bounds for the $U^4$ inverse theorem. Our cubic Goldreich-Levin algorithm is constructed from two main tools: an algorithmic $U^4$ inverse theorem and an arithmetic decomposition result in the style of the Frieze-Kannan graph regularity lemma. As one application of our main theorem we solve the problem of self-correction for cubic Reed-Muller codes beyond the list decoding radius. Additionally we give a purely combinatorial result: an improvement of the quantitative bounds on the $U^4$ inverse theorem., Comment: 51 pages

Automated real-time evaluation of counselor-client interaction is important for ensuring quality counseling but the rules are difficult to articulate. Recent advancements in machine learning methods show the possibility of learning such rules automatically. However, these methods often demand large scale and high quality counseling data, which are difficult to collect. To address this issue, we build an online counseling platform, which allows professional psychotherapists to provide free counseling services to those are in need. In exchange, we collect the counseling transcripts. Within a year of its operation, we manage to get one of the largest set of (675) transcripts of counseling sessions. To further leverage the valuable data we have, we label our dataset using both coarse- and fine-grained labels and use a set of pretraining techniques. In the end, we are able to achieve practically useful accuracy in both labeling system., Comment: 15 pages, 4 figures