Searcharxiv⌕ Search

arXiv subjects

Chao Yang

Publications and source records attributed to Chao Yang.

At least 127 records · Page 7Linked to original sources

Listwise Preference Alignment Optimization for Tail Item Recommendation

Preference alignment has achieved greater success on Large Language Models (LLMs) and drawn broad interest in recommendation research. Existing preference alignment methods for recommendation either require explicit reward modeling or only support pairwise preference comparison. The former directly increases substantial computational costs, while the latter hinders training efficiency on negative samples. Moreover, no existing effort has explored preference alignment solutions for tail-item recommendation. To bridge the above gaps, we propose LPO4Rec, which extends the Bradley-Terry model from pairwise comparison to listwise comparison, to improve the efficiency of model training. Specifically, we derive a closed form optimal policy to enable more efficient and effective training without explicit reward modeling. We also present an adaptive negative sampling and reweighting strategy to prioritize tail items during optimization and enhance performance in tail-item recommendations. Besides, we theoretically prove that optimizing the listwise preference optimization (LPO) loss is equivalent to maximizing the upper bound of the optimal reward. Our experiments on three public datasets show that our method outperforms 10 baselines by a large margin, achieving up to 50% performance improvement while reducing 17.9% GPU memory usage when compared with direct preference optimization (DPO) in tail-item recommendation. Our code is available at https://github.com/Yuhanleeee/LPO4Rec.

cs.IR↗

Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting

Implicit Neural Representation (INR) has demonstrated remarkable advances in the field of image representation but demands substantial GPU resources. GaussianImage recently pioneered the use of Gaussian Splatting to mitigate this cost, however, the slow training process limits its practicality, and the fixed number of Gaussians per image limits its adaptability to varying information entropy. To address these issues, we propose in this paper a generalizable and self-adaptive image representation framework based on 2D Gaussian Splatting. Our method employs a network to quickly generate a coarse Gaussian representation, followed by minimal fine-tuning steps, achieving comparable rendering quality of GaussianImage while significantly reducing training time. Moreover, our approach dynamically adjusts the number of Gaussian points based on image complexity to further enhance flexibility and efficiency in practice. Experiments on DIV2K and Kodak datasets show that our method matches or exceeds GaussianImage's rendering performance with far fewer iterations and shorter training times. Specifically, our method reduces the training time by up to one order of magnitude while achieving superior rendering performance with the same number of Gaussians.

cs.CV↗

A Glimpse of Satellite Galaxies in the Milky Way with the 2.5-meter Wide Field Survey Telescope (WFST): Bootes III and Draco

We carry out deep imaging of the Milky Way satellite galaxies, Bootes III and Draco, with WFST as one pilot observing program to demonstrate the capability of WFST. Combining catalogs with PS1 DR2 and Gaia DR3, we derive proper motions for candidate member stars in these two satellite galaxies over a 12-year time baseline, yielding uncertainties of ~1.8 mas/yr at 21 mag and ~3.0 mas/yr at 22 mag in the r band. The proper motions derived from bright and faint stars are consistent, indicating no significant variation in proper motion across stellar luminosity as these galaxies undergo tidal interactions with the MW. Meanwhile, we suggest that Bootes III represents the bound remnant of the progenitor galaxy that gave rise to the Styx stream, as evidenced by its elongated density profile and overdensity in both spatial and kinematic space. This is the first paper to use WFST to measure the proper motions of faint stars in Milky Way satellite galaxies. More detailed analyses will be presented in forthcoming papers from the wide field survey (WFS) program.

astro-ph.GA↗

Balmer Decrement and IRX Break in Tracing Dust Attenuation at Scales of Individual Star-forming Regions in NGC 628

We investigate the relationships between infrared excess (IRX=$L_{\rm IR}/L_{\rm UV}$) and Balmer decrement (${\rm H}α/{\rm H}β$) as indicators of dust attenuation for 609 ${\rm {H\,{\small II}}}$ regions at scales of $\sim 50-200$ pc in NGC 628, utilizing data from AstroSat, James Webb Space Telescope (JWST) and Multi Unit Spectroscopic Explorer (MUSE). Our findings indicate that about three fifths of the sample ${\rm {H\,{\small II}}}$ regions reside within the regime occupied by local star-forming galaxies (SFGs) along the dust attenuation correlation described by their corresponding color excess parameters $E(B-V)_{\rm IRX} = 0.51\,E(B-V)_{{\rm H}α/{\rm H}β}$. Nearly 27$\%$ of the sample exhibits $E(B-V)_{\rm IRX}> E(B-V)_{{\rm H}α/{\rm H}β}$, while a small fraction ($\sim 13\%$) displays significantly lower $E(B-V)_{\rm IRX}$ compared to $E(B-V)_{{\rm H}α/{\rm H}β}$. These results suggest that the correlation between the two dust attenuation indicators no longer holds for spatially resolved ${\rm {H\,{\small II}}}$ regions. Furthermore, the ratio of $E(B-V)_{\rm IRX}$ to $E(B-V)_{{\rm H}α/{\rm H}β}$ remains unaffected by various physical parameters of the ${\rm {H\,{\small II}}}$ regions, including star formation rate (SFR), SFR surface density, infrared luminosity ($L_{\rm IR}$), $L_{\rm IR}$ surface density, stellar mass, gas-phase metallicity, circularized radius, and the distance to galactic center. We argue that the ratio is primarily influenced by the evolution of surrounding interstellar medium (ISM) of the star-forming regions, transitioning from an early dense and thick phase to the late blown-away stage.

astro-ph.GA↗

Foundation Models for Atomistic Simulation of Chemistry and Materials

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale.

physics.chem-ph↗

Undecidability of Translational Tiling of the Plane with Four Tiles

The translational tiling problem, dated back to Wang's domino problem in the 1960s, is one of the most representative undecidable problems in the field of discrete geometry and combinatorics. Ollinger initiated the study of the undecidability of translational tiling with a fixed number of tiles in 2009, and proved that translational tiling of the plane with a set of $11$ polyominoes is undecidable. The number of polyominoes needed to obtain undecidability was reduced from $11$ to $7$ by Yang and Zhang, and then to $5$ by Kim. We show that translational tiling of the plane with a set of $4$ (disconnected) polyominoes is undecidable in this paper.

math.CO↗

Undecidability of Translational Tiling of the Plane with Orthogonally Convex Polyominoes

The first undecidability result on the tiling is the undecidability of translational tiling of the plane with Wang tiles, where there is an additional color matching requirement. Later, researchers obtained several undecidability results on translational tiling problems where the tilings are subject to the geometric shapes of the tiles only. However, all these results are proved by constructing tiles with extremely concave shapes. It is natural to ask: can we obtain undecidability results of translational tiling with convex tiles? Towards answering this question, we prove the undecidability of translational tiling of the plane with a set of 7 orthogonally convex polyominoes.

math.CO↗

Using Vision Language Models to Detect Students' Academic Emotion through Facial Expressions

Students' academic emotions significantly influence their social behavior and learning performance. Traditional approaches to automatically and accurately analyze these emotions have predominantly relied on supervised machine learning algorithms. However, these models often struggle to generalize across different contexts, necessitating repeated cycles of data collection, annotation, and training. The emergence of Vision-Language Models (VLMs) offers a promising alternative, enabling generalization across visual recognition tasks through zero-shot prompting without requiring fine-tuning. This study investigates the potential of VLMs to analyze students' academic emotions via facial expressions in an online learning environment. We employed two VLMs, Llama-3.2-11B-Vision-Instruct and Qwen2.5-VL-7B-Instruct, to analyze 5,000 images depicting confused, distracted, happy, neutral, and tired expressions using zero-shot prompting. Preliminary results indicate that both models demonstrate moderate performance in academic facial expression recognition, with Qwen2.5-VL-7B-Instruct outperforming Llama-3.2-11B-Vision-Instruct. Notably, both models excel in identifying students' happy emotions but fail to detect distracted behavior. Additionally, Qwen2.5-VL-7B-Instruct exhibits relatively high performance in recognizing students' confused expressions, highlighting its potential for practical applications in identifying content that causes student confusion.

cs.CV↗

SafeCoT: Improving VLM Safety with Minimal Reasoning

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages rule-based chain-of-thought (CoT) supervision to improve refusal behavior in VLMs. Unlike prior methods that rely on large-scale safety annotations or complex modeling, SafeCoT uses minimal supervision to help models reason about safety risks and make context-aware refusals. Experiments across multiple benchmarks show that SafeCoT significantly reduces overrefusal and enhances generalization, even with limited training data. Our approach offers a scalable solution for aligning VLMs with safety-critical objectives.

cs.AI↗

RePO: Replay-Enhanced Policy Optimization

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low data efficiency. To address this, we introduce Replay-Enhanced Policy Optimization (RePO), which leverages diverse replay strategies to retrieve off-policy samples from a replay buffer, allowing policy optimization based on a broader and more diverse set of samples for each prompt. Experiments on five LLMs across seven mathematical reasoning benchmarks demonstrate that RePO achieves absolute average performance gains of $18.4$ and $4.1$ points for Qwen2.5-Math-1.5B and Qwen3-1.7B, respectively, compared to GRPO. Further analysis indicates that RePO increases computational cost by $15\%$ while raising the number of effective optimization steps by $48\%$ for Qwen3-1.7B, with both on-policy and off-policy sample numbers set to $8$. The repository can be accessed at https://github.com/SihengLi99/RePO.

cs.CL↗

SOLIDGEO: Measuring Multimodal Spatial Math Reasoning in Solid Geometry

Geometry is a fundamental branch of mathematics and plays a crucial role in evaluating the reasoning capabilities of multimodal large language models (MLLMs). However, existing multimodal mathematics benchmarks mainly focus on plane geometry and largely ignore solid geometry, which requires spatial reasoning and is more challenging than plane geometry. To address this critical gap, we introduce SolidGeo, the first large-scale benchmark specifically designed to evaluate the performance of MLLMs on mathematical reasoning tasks in solid geometry. SolidGeo consists of 3,113 real-world K-12 and competition-level problems, each paired with visual context and annotated with difficulty levels and fine-grained solid geometry categories. Our benchmark covers a wide range of 3D reasoning subjects such as projection, unfolding, spatial measurement, and spatial vector, offering a rigorous testbed for assessing solid geometry. Through extensive experiments, we observe that MLLMs encounter substantial challenges in solid geometry math tasks, with a considerable performance gap relative to human capabilities on SolidGeo. Moreover, we analyze the performance, inference efficiency and error patterns of various models, offering insights into the solid geometric mathematical reasoning capabilities of MLLMs. We hope SolidGeo serves as a catalyst for advancing MLLMs toward deeper geometric reasoning and spatial intelligence.

cs.CG↗

Mitigating Object Hallucination via Robust Local Perception Search

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit hallucination phenomena, where the outputs appear plausible but do not align with the content of the images. To mitigate this issue, we introduce Local Perception Search (LPS), a decoding method during inference that is both simple and training-free, yet effectively suppresses hallucinations. This method leverages local visual prior information as a value function to correct the decoding process. Additionally, we observe that the impact of the local visual prior on model performance is more pronounced in scenarios with high levels of image noise. Notably, LPS is a plug-and-play approach that is compatible with various models. Extensive experiments on widely used hallucination benchmarks and noisy data demonstrate that LPS significantly reduces the incidence of hallucinations compared to the baseline, showing exceptional performance, particularly in noisy settings.

cs.CV↗

VLMs Can Aggregate Scattered Training Patches

One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-looking patches, scattered across many training samples. VLMs may then learn to piece these fragments together during training and generate harmful responses at inference, either from full images or text references. For instance, if trained on image patches from a bloody scene paired with the descriptions "safe," VLMs may later describe, the full image or a text reference to the scene, as "safe." We define the core ability of VLMs enabling this attack as $\textit{visual stitching}$ -- the ability to integrate visual information spread across multiple training samples that share the same textual descriptions. In our work, we first demonstrate visual stitching abilities in common open-source VLMs on three datasets where each image is labeled with a unique synthetic ID: we split each $(\texttt{image}, \texttt{ID})$ pair into $\{(\texttt{patch}, \texttt{ID})\}$ pairs at different granularity for finetuning, and we find that tuned models can verbalize the correct IDs from full images or text reference. Building on this, we simulate the adversarial data poisoning scenario mentioned above by using patches from dangerous images and replacing IDs with text descriptions like ``safe'' or ``unsafe'', demonstrating how harmful content can evade moderation in patches and later be reconstructed through visual stitching, posing serious VLM safety risks. Code is available at https://github.com/ZHZisZZ/visual-stitching.

cs.CV↗

Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making

Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabilities, while RL struggles with sample efficiency in vast action spaces. To bridge this gap, we propose Agents Co-Evolution (ACE), a synergistic framework between LLMs and RL agents for large-scale decision-making scenarios. ACE introduces a dual-role trajectory refinement mechanism where LLMs act as both Policy Actor and Value Critic during RL's training: the Actor refines suboptimal actions via multi-step reasoning and environment validation, while the Critic performs temporal credit assignment through trajectory-level reward shaping. Concurrently, RL agent enhances LLMs' task-specific decision-making with high-quality fine-tuning datasets generated via prioritized experience replay. Through extensive experiments across multiple power grid operation challenges with action spaces exceeding 60K discrete actions, ACE demonstrates superior performance over existing RL methods and LLM-based methods.

cs.AI↗

Adversarial Preference Learning for Robust LLM Alignment

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation, (2) the vast diversity of potential adversarial attacks, and (3) the risk of feedback bias and reward hacking. To address these challenges, we introduce Adversarial Preference Learning (APL), an iterative adversarial training method incorporating three key innovations. First, a direct harmfulness metric based on the model's intrinsic preference probabilities, eliminating reliance on external assessment. Second, a conditional generative attacker that synthesizes input-specific adversarial variations. Third, an iterative framework with automated closed-loop feedback, enabling continuous adaptation through vulnerability discovery and mitigation. Experiments on Mistral-7B-Instruct-v0.3 demonstrate that APL significantly enhances robustness, achieving 83.33% harmlessness win rate over the base model (evaluated by GPT-4o), reducing harmful outputs from 5.88% to 0.43% (measured by LLaMA-Guard), and lowering attack success rate by up to 65% according to HarmBench. Notably, APL maintains competitive utility, with an MT-Bench score of 6.59 (comparable to the baseline 6.78) and an LC-WinRate of 46.52% against the base model.

cs.LG↗

Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalance

RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions. Traditional RGB-T detectors assume balanced training data, where both modalities contribute equally. However, in real-world scenarios, modality degradation-due to environmental factors or technical issues-can lead to extreme modality imbalance, causing out-of-distribution (OOD) issues during testing and disrupting model convergence during training. This paper addresses these challenges by proposing a novel base-and-auxiliary detector architecture. We introduce a modality interaction module to adaptively weigh modalities based on their quality and handle imbalanced samples effectively. Additionally, we leverage modality pseudo-degradation to simulate real-world imbalances in training data. The base detector, trained on high-quality pairs, provides a consistency constraint for the auxiliary detector, which receives degraded samples. This framework enhances model robustness, ensuring reliable performance even under severe modality degradation. Experimental results demonstrate the effectiveness of our method in handling extreme modality imbalances~(decreasing the Missing Rate by 55%) and improving performance across various baseline detectors.

cs.CV↗

GPU acceleration of non-equilibrium Green's function calculation using OpenACC and CUDA FORTRAN

The numerical solution of the Kadanoff-Baym nonlinear integro-differential equations, which yields the non-equilibrium Green's functions (NEGFs) of quantum many-body systems, poses significant computational challenges due to its high computational complexity. In this work, we present efficient implementations of a numerical method for solving these equations on distributed-memory architectures, including many-core CPUs and multi-GPU systems. For CPU-based platforms, we adopt a hybrid MPI/OpenMP programming model to exploit both inter-node and intra-node parallelism. On GPU-accelerated systems, we implement the method using two distinct approaches: MPI/OpenACC and MPI/CUDA FORTRAN. Several optimization strategies are employed to enhance GPU performance, including techniques to maximize computational resource utilization and minimize the overhead associated with kernel launches and memory management. Although OpenACC is easy to use, CUDA FORTRAN provides more advanced features for configuring and managing multiple levels of concurrency, while also simplifying memory allocation and data movement between host and device. This flexibility translates into significant performance improvements. We compare the performance of the three implementations and demonstrate that the GPU-based approaches achieve substantial speedups over CPU-based implementations. Furthermore, both CPU and GPU versions exhibit excellent strong and weak scaling, confirming the scalability and efficiency of our approach for large-scale NEGF computations.

cs.DC↗

Ab initio many-fermion structure calculations on a quantum computer

To overcome the limitations of existing algorithms for solving self-bound quantum many-body problems -- such as those encountered in nuclear and particle physics -- that access only a restricted subset of energy levels and provide limited structural information, we introduce and demonstrate a novel quantum-classical approach capable of resolving the complete bound-state spectrum. This method also provides the total angular momentum $J$ associated with each eigenstate. Our approach is based on expressing the Hamiltonian in second-quantized form within a novel input model combined with a scan scheme, enabling broad applicability to configuration-interaction calculations across diverse fields. We apply this hybrid method to compute, for the first time, the bound-state spectrum together with corresponding $J$ values of ${^{20}O}$ using a realistic strong-interaction Hamiltonian. Our approach applies to hadron spectra and $J$ values solved in the relativistic Basis Light-Front Quantization approach.

nucl-th↗