3 citations · 8 across the 21 of their papers we have counts for
24 papers
Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
Dylan P. Wilson, Chengsong Huang, Jiaxin Huang
Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards. This is pu…
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Jinyuan Li, Chengsong Huang, Langlin Huang +4
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance…
EnvHarness: Awakening Static Worlds for Agent Learning
Chengsong Huang, Zifeng Wang, Rujun Han +14
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While r…
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Zhepei Wei, Xinyu Zhu, Wei-Lin Chen +3
Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving reasoning in large language models (LLMs), yet the underlying geometry of the res…
Process Rewards with Learned Reliability
Jinyuan Li, Langlin Huang, Chengsong Huang +5
Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore…
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Langlin Huang, Chengsong Huang, Jinyuan Li +3
Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Mode…
RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models
Jianwei Zhang, Chaoning Zhang, Sihan Cao +7
Large Vision-Language Models (LVLMs) suffer from prohibitive inference costs due to the massive number of visual tokens processed by the language decoder. Existing pruning methods…
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
Tong Zheng, Chengsong Huang, Runpeng Dai +9
Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-traj…
Training Data Efficiency in Multimodal Process Reward Models
Jinyuan Li, Chengsong Huang, Langlin Huang +4
Multimodal Process Reward Models (MPRMs) are central to step-level supervision for visual reasoning in MLLMs. Training MPRMs typically requires large-scale Monte Carlo (MC)-annotat…
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang +13
Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retr…
RelayLLM: Efficient Reasoning via Collaborative Decoding
Chengsong Huang, Tong Zheng, Langlin Huang +3
Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack t…
UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning
Yinxu Tang, Chengsong Huang, Jiaxin Huang +1
Knowledge Graph Question Answering (KGQA) has largely focused on entity-centric queries that return a single answer entity. However, many real-world questions are inherently relati…
VisPlay: Self-Evolving Vision-Language Models from Images
Yicheng He, Chengsong Huang, Zongxia Li +2
Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on hu…
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, e…
Sequence-Model-Guided Measurement Selection for Quantum State Learning
Jiaxin Huang, Yan Zhu, Giulio Chiribella +1
Characterization of quantum systems from experimental data is a central problem in quantum science and technology. But which measurements should be used to gather data in the first…
SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
Yanwei Ren, Haotian Zhang, Fuxiang Wu +4
Enhancing large language models by simply scaling up datasets has begun to yield diminishing returns, shifting the spotlight to data quality. Monte Carlo Tree Search (MCTS) has eme…
POSS: Position Specialist Generates Better Draft for Speculative Decoding
Langlin Huang, Chengsong Huang, Jixuan Leng +2
Speculative decoding accelerates Large Language Model (LLM) inference by using a small draft model to predict multiple tokens, and a large target model to verify these tokens in pa…
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
Jixuan Leng, Chengsong Huang, Langlin Huang +4
Existing reasoning evaluation frameworks for Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) predominantly assess either text-based reasoning or vision-langua…
Efficient Test-Time Scaling via Self-Calibration
Chengsong Huang, Langlin Huang, Jixuan Leng +2
Increasing test-time computation is a straightforward approach to enhancing the quality of responses in Large Language Models (LLMs). While Best-of-N sampling and Self-Consistency…
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
Xinyu Zhang, Yuxuan Dong, Yanrui Wu +6
Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based re…
Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
Chengsong Huang, Langlin Huang, Jiaxin Huang
In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model…
Taming Overconfidence in LLMs: Reward Calibration in RLHF
Jixuan Leng, Chengsong Huang, Banghua Zhu +1
Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfide…
GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
Lecheng Kong, Jiarui Feng, Hao Liu +4
Foundation models, such as Large Language Models (LLMs) or Large Vision Models (LVMs), have emerged as one of the most powerful tools in the respective fields. However, unlike text…
Optimizing Language Model's Reasoning Abilities with Weak Supervision
Yongqi Tong, Sizhe Wang, Dawei Li +6
While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts.…