arXiv subjects

Zhaofeng He

Publications and source records attributed to Zhaofeng He.

At least 37 records · Page 2Linked to original sources

arXiv2025

Simulation-Free PSRO: Removing Game Simulation from Policy Space Response Oracles

Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, the computational cost of PSRO has become a significant limitation to its practical application. Our analysis shows that game simulation is the primary bottleneck in PSRO's runtime. To address this issue, we conclude the concept of Simulation-Free PSRO and summarize existing methods that instantiate this concept. Additionally, we propose a novel Dynamic Window-based Simulation-Free PSRO, which introduces the concept of a strategy window to replace the original strategy set maintained in PSRO. The number of strategies in the strategy window is limited, thereby simplifying opponent strategy selection and improving the robustness of the best response. Moreover, we use Nash Clustering to select the strategy to be eliminated, ensuring that the number of strategies within the strategy window is effectively limited. Our experiments across various environments demonstrate that the Dynamic Window mechanism significantly reduces exploitability compared to existing methods, while also exhibiting excellent compatibility. Our code is available at https://github.com/enochliu98/SF-PSRO.

cs.MA↗

arXiv2025

Do MLLMs Really Understand the Charts?

Although Multimodal Large Language Models (MLLMs) have demonstrated increasingly impressive performance in chart understanding, most of them exhibit alarming hallucinations and significant performance degradation when handling non-annotated charts. We argue that current MLLMs rely largely on visual recognition rather than visual reasoning to interpret the charts, and visual estimation of numerical values is one of the most fundamental capabilities in chart understanding that require complex visual reasoning. To prove this, we introduce ChartVRBench, a benchmark meticulously designed to isolate and evaluate visual reasoning ability in chart understanding. Furthermore, we propose ChartVR-3B/7B trained with a novel Visual Reasoning Reinforcement Finetuning (VR-RFT) strategy to strengthen genuine chart visual reasoning abilities. Extensive experiments show that ChartVR achieves superior performance on ChartVRBench, outperforming even powerful proprietary models. Moreover, the visual reasoning skills cultivated by the proposed VR-RFT demonstrate strong generalization, leading to significant performance gains across a diverse suite of public chart understanding benchmarks. The code and dataset will be publicly available upon publication.

cs.CL↗

arXiv2025

Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose \textbf{STA-Attention}, a framework that utilizes Top-K Sparse Autoencoders (SAEs) to decompose the KV cache into interpretable ``semantic atoms.'' Unlike standard $L_1$-regularized SAEs, our Top-K approach eliminates shrinkage bias, preserving the precise dot-product geometry required for attention. Our analysis uncovers a fundamental \textbf{Key-Value Asymmetry}: while Key vectors serve as highly sparse routers dominated by a ``Semantic Elbow,'' deep Value vectors carry dense content payloads requiring a larger budget. Based on this structure, we introduce a Dual-Budget Strategy that selectively preserves the most informative semantic components while filtering representational noise. Experiments on Yi-6B, Mistral-7B, Qwen2.5-32B, and others show that our semantic reconstructions maintain perplexity and zero-shot performance comparable to the original models, effectively bridging the gap between mechanistic interpretability and faithful attention modeling.

cs.LG↗

arXiv2025

Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis

Under extremely low-light conditions, novel view synthesis (NVS) faces severe degradation in terms of geometry, color consistency, and radiometric stability. Standard 3D Gaussian Splatting (3DGS) pipelines fail when applied directly to underexposed inputs, as independent enhancement across views causes illumination inconsistencies and geometric distortion. To address this, we present DTGS, a unified framework that tightly couples Retinex-inspired illumination decomposition with thermal-guided 3D Gaussian Splatting for illumination-invariant reconstruction. Unlike prior approaches that treat enhancement as a pre-processing step, DTGS performs joint optimization across enhancement, geometry, and thermal supervision through a cyclic enhancement-reconstruction mechanism. A thermal supervisory branch stabilizes both color restoration and geometry learning by dynamically balancing enhancement, structural, and thermal losses. Moreover, a Retinex-based decomposition module embedded within the 3DGS loop provides physically interpretable reflectance-illumination separation, ensuring consistent color and texture across viewpoints. To evaluate our method, we construct RGBT-LOW, a new multi-view low-light thermal dataset capturing severe illumination degradation. Extensive experiments show that DTGS significantly outperforms existing low-light enhancement and 3D reconstruction baselines, achieving superior radiometric consistency, geometric fidelity, and color stability under extreme illumination.

cs.CV↗

arXiv2025

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models

Large language models (LLMs) have demonstrated remarkable reasoning and planning capabilities, driving extensive research into task decomposition. Existing task decomposition methods focus primarily on memory, tool usage, and feedback mechanisms, achieving notable success in specific domains, but they often overlook the trade-off between performance and cost. In this study, we first conduct a comprehensive investigation on task decomposition, identifying six categorization schemes. Then, we perform an empirical analysis of three factors that influence the performance and cost of task decomposition: categories of approaches, characteristics of tasks, and configuration of decomposition and execution models, uncovering three critical insights and summarizing a set of practical principles. Building on this analysis, we propose the Select-Then-Decompose strategy, which establishes a closed-loop problem-solving process composed of three stages: selection, execution, and verification. This strategy dynamically selects the most suitable decomposition approach based on task characteristics and enhances the reliability of the results through a verification module. Comprehensive evaluations across multiple benchmarks show that the Select-Then-Decompose consistently lies on the Pareto frontier, demonstrating an optimal balance between performance and cost. Our code is publicly available at https://github.com/summervvind/Select-Then-Decompose.

cs.CL↗

arXiv2025

A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings

Large Reasoning Models (LRMs) achieve superior performance by extending the thought length. However, a lengthy thinking trajectory leads to reduced efficiency. Most of the existing methods are stuck in the assumption of overthinking and attempt to reason efficiently by compressing the Chain-of-Thought, but this often leads to performance degradation. To address this problem, we introduce A*-Thought, an efficient tree search-based unified framework designed to identify and isolate the most essential thoughts from the extensive reasoning chains produced by these models. It formulates the reasoning process of LRMs as a search tree, where each node represents a reasoning span in the giant reasoning space. By combining the A* search algorithm with a cost function specific to the reasoning path, it can efficiently compress the chain of thought and determine a reasoning path with high information density and low cost. In addition, we also propose a bidirectional importance estimation mechanism, which further refines this search process and enhances its efficiency beyond uniform sampling. Extensive experiments on several advanced math tasks show that A*-Thought effectively balances performance and efficiency over a huge search space. Specifically, A*-Thought can improve the performance of QwQ-32B by 2.39$\times$ with low-budget and reduce the length of the output token by nearly 50% with high-budget. The proposed method is also compatible with several other LRMs, demonstrating its generalization capability. The code can be accessed at: https://github.com/AI9Stars/AStar-Thought.

cs.CL↗

arXiv2025

OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing

While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactive worlds. Static benchmarks lack agency, while interactive benchmarks suffer from a severe modal bottleneck, typically ignoring crucial auditory and temporal cues. To bridge this evaluation chasm, we introduce OmniPlay, a diagnostic benchmark designed not just to evaluate, but to probe the fusion and reasoning capabilities of agentic models across the full sensory spectrum. Built on a core philosophy of modality interdependence, OmniPlay comprises a suite of five game environments that systematically create scenarios of both synergy and conflict, forcing agents to perform genuine cross-modal reasoning. Our comprehensive evaluation of six leading omni-modal models reveals a critical dichotomy: they exhibit superhuman performance on high-fidelity memory tasks but suffer from systemic failures in challenges requiring robust reasoning and strategic planning. We demonstrate that this fragility stems from brittle fusion mechanisms, which lead to catastrophic performance degradation under modality conflict and uncover a counter-intuitive "less is more" paradox, where removing sensory information can paradoxically improve performance. Our findings suggest that the path toward robust AGI requires a research focus beyond scaling to explicitly address synergistic fusion. Our platform is available for anonymous review at https://github.com/fuqingbie/omni-game-benchmark.

cs.AI↗

arXiv2025

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for policy rollout, and (2) insufficient high-quality agent-environment interactions for policy learning. To address these challenges, we propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner. DART separates the training system into four asynchronous modules: environment cluster, rollout service, data manager, and trainer. This design enables non-blocking communication, asynchronous training, rollout-wise trajectory sampling, and per-worker model synchronization, significantly improving the system efficiency: 1.6*GPU utilization for rollout, 1.9* training throughput, and 5.5* environment utilization. To facilitate effective learning from abundant samples, we introduce an adaptive data curation scheme: (1) pre-collecting successful trajectories for challenging tasks to supplement sparse success in online sampling; (2) dynamically adjusting rollout numbers and trajectory lengths based on task difficulty; (3) training selectively on high-entropy steps to prioritize critical decisions; (4) stabilizing learning via truncated importance sampling for policy mismatch between policy rollout and updating. On the OSWorld benchmark, DART-GUI-7B achieves a 42.13% task success rate, a 14.61% absolute gain over the base model, and 7.34% higher than open-source SOTA. We will fully open-source our training framework, data, and model checkpoints via computer-use-agents.github.io/dart-gui, which we believe is a timely contribution to the open-source community of agentic RL training.

cs.LG↗

arXiv2025

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding

Articulated objects pose diverse manipulation challenges for robots. Since their internal structures are not directly observable, robots must adaptively explore and refine actions to generate successful manipulation trajectories. While existing works have attempted cross-category generalization in adaptive articulated object manipulation, two major challenges persist: (1) the geometric diversity of real-world articulated objects complicates visual perception and understanding, and (2) variations in object functions and mechanisms hinder the development of a unified adaptive manipulation strategy. To address these challenges, we propose AdaRPG, a novel framework that leverages foundation models to extract object parts, which exhibit greater local geometric similarity than entire objects, thereby enhancing visual affordance generalization for functional primitive skills. To support this, we construct a part-level affordance annotation dataset to train the affordance model. Additionally, AdaRPG utilizes the common knowledge embedded in foundation models to reason about complex mechanisms and generate high-level control codes that invoke primitive skill functions based on part affordance inference. Simulation and real-world experiments demonstrate AdaRPG's strong generalization ability across novel articulated object categories.

cs.RO↗

arXiv2025

SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insights

With the rise and development of computer vision and LLMs, intelligence is everywhere, especially for people and cars. However, for tremendous food attributes (such as origin, quantity, weight, quality, sweetness, etc.), existing research still mainly focuses on the study of categories. The reason is the lack of a large and comprehensive benchmark for food. Besides, many food attributes (such as sweetness, weight, and fine-grained categories) are challenging to accurately percept solely through RGB cameras. To fulfill this gap and promote the development of intelligent food analysis, in this paper, we built the first large-scale spectral food (SFOOD) benchmark suite. We spent a lot of manpower and equipment costs to organize existing food datasets and collect hyperspectral images of hundreds of foods, and we used instruments to experimentally determine food attributes such as sweetness and weight. The resulting benchmark consists of 3,266 food categories and 2,351 k data points for 17 main food categories. Extensive evaluations find that: (i) Large-scale models are still poor at digitizing food. Compared to people and cars, food has gradually become one of the most difficult objects to study; (ii) Spectrum data are crucial for analyzing food properties (such as sweetness). Our benchmark will be open source and continuously iterated for different food analysis tasks.

cs.CV↗

arXiv2025

Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation

Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents. Addressing this challenge is highly complex, and researchers have proposed two simplified scenarios, Multi-agent reinforcement learning for zero-shot learning and Ad-Hoc Teamwork. Building on these foundations, we propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation (ACCA), which evaluates an agent to generalize across diverse scenarios, tasks, and interactions with both unfamiliar opponents and teammates. In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents. We introduce a new modeling approach, Multi-Retrieval and Dynamic Generation (MRDG), that effectively models both teammates and opponents using their behavioral trajectories. This method incorporates a positional encoder for varying team sizes and a hypernetwork module to boost agents' learning and adaptive capabilities. Additionally, a viewpoint alignment module harmonizes the observational perspectives of retrieved teammates and opponents with the learning agent. Extensive tests in benchmark scenarios like SMAC, Overcooked-AI, and Melting Pot show that MRDG significantly improves robust collaboration and competition with unseen teammates and opponents, surpassing established baselines. Our code is available at: https://github.com/vcis-wangchenxu/MRDG.git

cs.MA↗

arXiv2025

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist. The lack of a benchmark for mixed-source misinformation has hindered progress in this field. To address this, we introduce MMFakeBench, the first comprehensive benchmark for mixed-source MMD. MMFakeBench includes 3 critical sources: textual veracity distortion, visual veracity distortion, and cross-modal consistency distortion, along with 12 sub-categories of misinformation forgery types. We further conduct an extensive evaluation of 6 prevalent detection methods and 15 Large Vision-Language Models (LVLMs) on MMFakeBench under a zero-shot setting. The results indicate that current methods struggle under this challenging and realistic mixed-source MMD setting. Additionally, we propose MMD-Agent, a novel approach to integrate the reasoning, action, and tool-use capabilities of LVLM agents, significantly enhancing accuracy and generalization. We believe this study will catalyze future research into more realistic mixed-source multimodal misinformation and provide a fair evaluation of misinformation detection methods.

cs.CV↗

arXiv2025

AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning

Articulated object manipulation is a critical capability for robots to perform various tasks in real-world scenarios. Composed of multiple parts connected by joints, articulated objects are endowed with diverse functional mechanisms through complex relative motions. For example, a safe consists of a door, a handle, and a lock, where the door can only be opened when the latch is unlocked. The internal structure, such as the state of a lock or joint angle constraints, cannot be directly observed from visual observation. Consequently, successful manipulation of these objects requires adaptive adjustment based on trial and error rather than a one-time visual inference. However, previous datasets and simulation environments for articulated objects have primarily focused on simple manipulation mechanisms where the complete manipulation process can be inferred from the object's appearance. To enhance the diversity and complexity of adaptive manipulation mechanisms, we build a novel articulated object manipulation environment and equip it with 9 categories of objects. Based on the environment and objects, we further propose an adaptive demonstration collection and 3D visual diffusion-based imitation learning pipeline that learns the adaptive manipulation policy. The effectiveness of our designs and proposed method is validated through both simulation and real-world experiments. Our project page is available at: https://adamanip.github.io

cs.RO↗

arXiv2024

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios within Reinforcement Learning. However, these works encounter challenges in extending their capabilities to new tasks. Recent approaches integrate textual guidance or visual trajectory into decision networks to provide task-specific contextual cues, representing a promising direction. However, it is observed that relying solely on textual guidance or visual trajectory is insufficient for accurately conveying the contextual information of tasks. This paper explores enhanced forms of task guidance for agents, enabling them to comprehend gameplay instructions, thereby facilitating a "read-to-play" capability. Drawing inspiration from the success of multimodal instruction tuning in visual tasks, we treat the visual-based RL task as a long-horizon vision task and construct a set of multimodal game instructions to incorporate instruction tuning into a decision transformer. Experimental results demonstrate that incorporating multimodal game instructions significantly enhances the decision transformer's multitasking and generalization capabilities.

cs.AI↗

arXiv2024

Learning Uniformly Distributed Embedding Clusters of Stylistic Skills for Physically Simulated Characters

Learning natural and diverse behaviors from human motion datasets remains challenging in physics-based character control. Existing conditional adversarial models often suffer from tight and biased embedding distributions where embeddings from the same motion are closely grouped in a small area and shorter motions occupy even less space. Our empirical observations indicate this limits the representational capacity and diversity under each skill. An ideal latent space should be maximally packed by all motion's embedding clusters. In this paper, we propose a skill-conditioned controller that learns diverse skills with expressive variations. Our approach leverages the Neural Collapse phenomenon, a natural outcome of the classification-based encoder, to uniformly distributed cluster centers. We additionally propose a novel Embedding Expansion technique to form stylistic embedding clusters for diverse skills that are uniformly distributed on a hypersphere, maximizing the representational area occupied by each skill and minimizing unmapped regions. This maximally packed and uniformly distributed embedding space ensures that embeddings within the same cluster generate behaviors conforming to the characteristics of the corresponding motion clips, yet exhibiting noticeable variations within each cluster. Compared to existing methods, our controller not only generates high-quality, diverse motions covering the entire dataset but also achieves superior controllability, motion coverage, and diversity under each skill. Both qualitative and quantitative results confirm these traits, enabling our controller to be applied to a wide range of downstream tasks and serving as a cornerstone for diverse applications.

cs.GR↗

arXiv2024

Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner

Flexible and accurate drag-based editing is a challenging task that has recently garnered significant attention. Current methods typically model this problem as automatically learning "how to drag" through point dragging and often produce one deterministic estimation, which presents two key limitations: 1) Overlooking the inherently ill-posed nature of drag-based editing, where multiple results may correspond to a given input, as illustrated in Fig.1; 2) Ignoring the constraint of image quality, which may lead to unexpected distortion. To alleviate this, we propose LucidDrag, which shifts the focus from "how to drag" to "what-then-how" paradigm. LucidDrag comprises an intention reasoner and a collaborative guidance sampling mechanism. The former infers several optimal editing strategies, identifying what content and what semantic direction to be edited. Based on the former, the latter addresses "how to drag" by collaboratively integrating existing editing guidance with the newly proposed semantic guidance and quality guidance. Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator. Both qualitative and quantitative comparisons demonstrate the superiority of LucidDrag over previous methods.

cs.CV↗

arXiv2024

Generative Iris Prior Embedded Transformer for Iris Restoration

Iris restoration from complexly degraded iris images, aiming to improve iris recognition performance, is a challenging problem. Due to the complex degradation, directly training a convolutional neural network (CNN) without prior cannot yield satisfactory results. In this work, we propose a generative iris prior embedded Transformer model (Gformer), in which we build a hierarchical encoder-decoder network employing Transformer block and generative iris prior. First, we tame Transformer blocks to model long-range dependencies in target images. Second, we pretrain an iris generative adversarial network (GAN) to obtain the rich iris prior, and incorporate it into the iris restoration process with our iris feature modulator. Our experiments demonstrate that the proposed Gformer outperforms state-of-the-art methods. Besides, iris recognition performance has been significantly improved after applying Gformer.

eess.IV↗

arXiv2024

FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs

The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors. However, the insulated nature of training restricts the capability of classical detectors to obtain open-world facts. While Large Vision-Language Models (LVLMs) have encoded rich world knowledge, they are not inherently tailored for combating fake news and struggle to comprehend local forgery details. In this paper, we propose FKA-Owl, a novel framework that leverages forgery-specific knowledge to augment LVLMs, enabling them to reason about manipulations effectively. The augmented forgery-specific knowledge includes semantic correlation between text and images, and artifact trace in image manipulation. To inject these two kinds of knowledge into the LVLM, we design two specialized modules to establish their representations, respectively. The encoded knowledge embeddings are then incorporated into LVLMs. Extensive experiments on the public benchmark demonstrate that FKA-Owl achieves superior cross-domain performance compared to previous methods. Code is publicly available at https://liuxuannan.github.io/FKA_Owl.github.io/.

cs.CL↗