22 papers
TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
Xiangyu Li, Tianyi Wang, Zhihao Dou +2
Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video generation, in which a selected act…
GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning
Ruiyang Wang, Hao-Lun Hsu, Swarajh Mehta +3
Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constraints, recover from planning e…
AMRM-Pure: Semantic-Preserving Adversarial Purification
Zhihao Dou, Zhiqiang Gao, Dongfei Cui +6
Adversarial purification is a defense technique that employs generative models to remove adversarial perturbations. Current methods often rely on powerful generators, typically dif…
ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models
Zhihao Dou, Qinjian Zhao, Zhiqiang Gao +1
Vision--Language Models (VLMs) are increasingly deployed in safety-critical applications, yet remain vulnerable to backdoor attacks. Existing methods primarily manipulate final out…
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existi…
CoRe-Code: Collaborative Reinforcement Learning for Code Generation
Zhihao Dou, Qinjian Zhao, Zhongwei Wan +2
Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally…
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusabl…
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
Wang Yang, Chaoda Song, Xinpeng Li +7
Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficul…
ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning
Yuhan Shui, Ruobin Jin, Zhihao Dou +1
Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highl…
Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models
Qingtao Pan, Zhihao Dou, Shuo Li
Large Multimodal Models (LMMs) struggle to adapt varying computational budgets due to numerous visual tokens. Previous methods attempted to reduce the number of visual tokens befor…
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
Zhongwei Wan, Yun Shen, Zhihao Dou +9
Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. P…
SecureSplit: Mitigating Backdoor Attacks in Split Learning
Zhihao Dou, Dongfei Cui, Weida Wang +7
Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct fea…
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12
Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…
Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
Zhihao Dou, Qinjian Zhao, Zhongwei Wan +10
Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global plannin…
SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
Qinjian Zhao, Jiaqi Wang, Zhiqiang Gao +3
Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as j…
CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
Weida Wang, Dongchen Huang, Jiatong Li +32
We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than…
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
Zhongwei Wan, Zhihao Dou, Che Liu +11
Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-…
Toward Malicious Clients Detection in Federated Learning
Zhihao Dou, Jiaqi Wang, Wei Sun +2
Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL in…
Discrete Wavelet Transform-Based Capsule Network for Hyperspectral Image Classification
Zhiqiang Gao, Jiaqi Wang, Hangchi Shen +3
Hyperspectral image (HSI) classification is a crucial technique for remote sensing to build large-scale earth monitoring systems. HSI contains much more information than traditiona…
Adversarial Attacks to Multi-Modal Models
Zhihao Dou, Xin Hu, Haibo Yang +2
Multi-modal models have gained significant attention due to their powerful capabilities. These models effectively align embeddings across diverse data modalities, showcasing superi…
Defending against Jailbreak through Early Exit Generation of Large Language Models
Chongwen Zhao, Zhihao Dou, Kaizhu Huang
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models fo…
Self-supervised asymmetric deep hashing with margin-scalable constraint
Zhengyang Yu, Song Wu, Zhihao Dou +1
Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative…