1 citations · 4 across the 17 of their papers we have counts for
19 papers
Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation
Yinuo Zhang, Bingshuo Liu, Zhiying Tu +6
This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-…
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
Yang Tian, Rui Wang, Xumeng Wen +5
Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide lim…
SkillWiki: A Living Knowledge Infrastructure for Agent Skills
Dingcheng Huang, Yuda Ding, Bingshuo Liu +8
While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki…
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian, Xianliang Yang, Yinuo ma +6
Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher rewar…
MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction
Zizheng Zhang, Yiming Li, Justin Xu +6
In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate this process, act…
RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
Haitian Zhong, Jixiu Zhai, Lei Song +3
Multi-turn tool calling is challenging for Large Language Models (LLMs) because rewards are sparse and exploration is expensive. A common recipe, SFT followed by GRPO, can stall wh…
Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning
Ling Zhang, Xianliang Yang, Juwon Yu +4
Fine-tuning large pretrained language models is a common approach for aligning them with human preferences, but noisy or off-target examples can dilute supervision. While small, we…
In-Context Compositional Q-Learning for Offline Reinforcement Learning
Qiushui Xu, Yuhao Huang, Yushu Jiang +4
Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inad…
Sample-efficient LLM Optimization with Reset Replay
Zichuan Liu, Jinyu Wang, Lei Song +1
Recent advancements in LLM post-training, particularly through reinforcement learning and preference optimization, are key to boosting their reasoning capabilities. However, these…
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
Yiyuan Yang, Zichuan Liu, Lei Song +6
Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for trans…
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
Xianliang Yang, Ling Zhang, Haolong Qian +2
Heuristic algorithms play a vital role in solving combinatorial optimization (CO) problems, yet traditional designs depend heavily on manual expertise and struggle to generalize ac…
Learning to Select In-Context Demonstration Preferred by Large Language Model
Zheng Zhang, Shaocheng Lan, Lei Song +3
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent…
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
Wei Yang, Jingjing Fu, Rui Wang +3
Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowl…
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Jinyu Wang, Jingjing Fu, Rui Wang +2
Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often str…
C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
Ruohong Liu, Yuxin Pan, Linjie Xu +4
Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences. However, previou…
Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement Learning
Wenhao Zhao, Qiushui Xu, Linjie Xu +4
Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL)…
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Yifan Xia, Xianliang Yang, Zichuan Liu +3
Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models…
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
Linjie Xu, Zichuan Liu, Alexander Dockhorn +4
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MA…
Protecting Your LLMs with Information Bottleneck
Zichuan Liu, Zefan Wang, Linjie Xu +6
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to et…