57 citations · 715 across the 196 of their papers we have counts for
202 papers
From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations
Yixin Yang, Yue Wang, Fandong Meng +1
Large reasoning models generate reasoning trajectories token by token. At a given prefix, multiple next-token candidates may be plausible, yet shape subsequent reasoning and differ…
Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning
Rui Qi, Yufeng Chen, Yunlong Liang +6
In multilingual scenarios, queries with equivalent semantics but in different languages could guide the model into different reasoning trajectories, leading to performance disparit…
SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents
Chaoqun Cui, Hao Zhou, Meiqi Chen +2
Long-horizon software engineering (SWE) agents trained with reinforcement learning with verifiable rewards (RLVR) typically receive only terminal outcome supervision, making it dif…
Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper
Rongjin Li, Yuanxin Liu, Hao Zhou +3
Multimodal large language models (MLLMs) are increasingly capable scientific assistants, yet they remain far from fully autonomous research. This transition requires models to acti…
PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows
Hongliang Li, Yijin Liu, Zhiwei Zhang +5
While Large Language Model (LLM) agents excel at monolingual long-horizon planning and tool use, enterprise workflows inherently require processing multilingual resources across ex…
Self-Improving Large Language Models via Progressive Experience Evolution
Shijie Ren, Xiting Wang, Meng Li +8
Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction expe…
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Xinyan Guan, Jiali Zeng, Chunlei Xin +5
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivatio…
EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge
Yunhan Wang, Jiaan Wang, Lianzhe Huang +2
Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely…
Enhancing LLM Metacognition via Cognitive Pairwise Training
Weitao Li, Hao Zhou, Xuanyu Lei +11
Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when…
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
Zhiyu Xu, Lean Wang, Yuanxin Liu +5
Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire continually evolving domain-sp…
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Yuancheng Wei, Linli Yao, Lei Li +4
Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust e…
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
Kunquan Li, Yingxue Zhang, Fandong Meng +2
Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). While most approaches adopt a 'pre-thinking' paradigm and benefi…
Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning
Yongyu Mu, Jiali Zeng, Fandong Meng +2
Through encouraging self-exploration, reinforcement learning from verifiable rewards (RLVR) has significantly advanced the mathematical reasoning capabilities of large language mod…
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Hui Zhang, Juntao Liu, Zongkai Liu +4
Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond tradition…
SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
Yijie Chen, Yijin Liu, Fandong Meng
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has emerged as the standard post-training paradigm for large language models (LLMs). However, the conventional…
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
Zhexin Zhang, Yida Lu, Junfeng Fang +8
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…
General learned delegation by clones
Darren Li, Meiqi Chen, Chenze Shao +2
Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference bud…
How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
Liyan Xu, Mo Yu, Fandong Meng +1
Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden s…
Figure It Out: Improve the Frontier of Reasoning with Executable Visual States
Meiqi Chen, Fandong Meng, Jie Zhou
Complex reasoning problems often involve implicit spatial and geometric relationships that are not explicitly encoded in text. While recent reasoning models perform well across man…
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
Yuxiang Huang, Mingye Li, Xu Han +7
The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods e…
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time
Fangxu Yu, Ziyao Lu, Liqiang Niu +2
Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches pr…
Readability-Robust Code Summarization via Meta Curriculum Learning
Wenhao Zeng, Yitian Chai, Hao Zhou +3
Code summarization has emerged as a fundamental technique in the field of program comprehension. While code language models have shown significant advancements, the current models…
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
Chulun Zhou, Chunkang Zhang, Guoxin Yu +4
Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intens…
Efficient Covariance Estimation for Sparsified Functional Data
Sijie Zheng, Fandong Meng, Jie Zhou
Motivated by recent work involving the analysis of leveraging spatial correlations in sparsified mean estimation, we present a novel procedure for constructing covariance estimator…