12 citations · 60 across the 72 of their papers we have counts for
74 papers
State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models
Mingxu Chai, Chenyu Liu, Ziyu Shen +7
Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model (VLM)-based parsing approach…
A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
Bing Shao, Jiazheng Zhang, Long Ma +12
On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens rem…
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
Zhiheng Xi, Dingwen Yang, Jiaqi Liu +21
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic eval…
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
Heajun An, Qi Zhang, Vedanth Achanta +1
Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existi…
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
Hao Chen, Qi Zhang, Liyao Li +7
Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selecti…
HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers
Ming Zhang, Qiyuan Peng, Yinxi Wei +16
Existing logic benchmarks primarily measure models' ability to answer reasoning questions directly. Scalable benchmarks often generate text from formal structures, which makes answ…
Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
Jiazheng Zhang, Ziche Fu, Junrui Shen +17
Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existi…
Prefix-Adaptive Block Diffusion for Efficient Document Recognition
Mingxu Chai, Ziyu Shen, Chenyu Liu +3
Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing. However, existing BDMs bind…
FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
Caishuang Huang, Yang Qiao, Rongyu Zhang +8
Tool-use capabilities are vital for Large Language Models (LLMs) in finance, a domain characterized by massive investment targets and data-intensive inquiries. However, existing da…
CCTU: A Benchmark for Tool Use under Complex Constraints
Junjie Ye, Guoqiang Zhang, Wenjie Fu +4
Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such…
Steering LLMs via Scalable Interactive Oversight
Enyu Zhou, Zhiheng Xi, Long Ma +9
As Large Language Models increasingly automate complex, long-horizon tasks such as \emph{vibe coding}, a supervision gap has emerged. While models excel at execution, users often s…
CL-bench: A Benchmark for Context Learning
Shihan Dou, Ming Zhang, Zhangyue Yin +24
Current language models (LMs) excel at reasoning over prompts using pre-trained knowledge. However, real-world tasks are far more complex and context-dependent: models must learn f…
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
Deming Ding, Shichun Liu, Enhui Yang +12
Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are…
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
Zhiheng Xi, Chenyang Liao, Guanyu Li +12
Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation,…
Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
Xin Guo, Zhiheng Xi, Yiwen Ding +6
Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models (LVLMs), where models explore and learn from successf…
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
Senjie Jin, Lu Chen, Zhiheng Xi +9
Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasonin…
Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
Zhiheng Xi, Jixuan Huang, Xin Guo +15
Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typ…
SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
Yulong Chen, Qi Zhang, Jiawen Zhang +4
Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defens…
CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challenges
Hui Li, Changhao Jiang, Hongyu Wang +11
The ability to reason from audio, including speech, environmental sounds, and music, is essential for AI agents to interact effectively in real-world scenarios. Existing benchmarks…
Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation
Jianxiang Zang
The reward model (RM), as the core component of reinforcement learning from human feedback (RLHF) for large language models (LLMs), responsible for providing reward signals to gene…
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
Zhiheng Xi, Guanyu Li, Yutao Fan +13
In this paper, we introduce BMMR, a large-scale bilingual, multimodal, multi-disciplinary reasoning dataset for the community to develop and evaluate large multimodal models (LMMs)…
Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
Zhihao Zhang, Qiaole Dong, Qi Zhang +12
Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. W…
Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion
Jianxiang Zang, Meiling Ning, Yongda Wei +7
Recently, the concept of ``compression as intelligence'' has provided a novel informatics metric perspective for language models (LMs), emphasizing that highly structured represent…
Improving RL Exploration for LLM Reasoning through Retrospective Replay
Shihan Dou, Muling Wu, Jingwen Xu +4
Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essen…