2 citations · 10 across the 23 of their papers we have counts for
23 papers
Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
Dong Li, Sixuan Mi, Zihao Ye +10
Unraveling reaction mechanisms is central to modern chemistry, yet automating these investigations remains challenging because computational workflows still rely heavily on expert…
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Junqi Gao, Dazhi Zhang, Zhichang Guo +3
Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dyna…
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
Fangyuan Li, Pengfei Li, Shijie Wang +4
Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off:…
MARTI-MARS: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation
Shijie Wang, Pengfei Li, Yikun Fu +21
While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in co…
PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness
Junqi Gao, Zhichang Guo, Dazhi Zhang +3
Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of…
A Survey of Reinforcement Learning for Large Reasoning Models
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontie…
ReviewRL: Towards Automated Scientific Review with RL
Sihang Zeng, Kai Tian, Kaiyan Zhang +9
Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches strugg…
Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
Junqi Gao, Xiang Zou, YIng Ai +4
Graph Retrieval Augmented Generation (GraphRAG) effectively enhances external knowledge integration capabilities by explicitly modeling knowledge relationships, thereby improving t…
Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
Junqi Gao, Zhichang Guo, Dazhi Zhang +5
Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. Whi…
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
Jian Zhao, Runze Liu, Kaiyan Zhang +8
Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However…
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Runze Liu, Junqi Gao, Jian Zhao +5
Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, cu…
Fast and Slow Gradient Approximation for Binary Neural Network Optimization
Xinquan Chen, Junqi Gao, Biqing Qi +4
Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantizat…
Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization
Biqing Qi, Zhouyi Qian, Yiang Luo +4
As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting thei…
An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
Dong Li, Aijia Zhang, Junqi Gao +1
Incremental graph learning has gained significant attention for its ability to address the catastrophic forgetting problem in graph representation learning. However, traditional me…
SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning
Biqing Qi, Junqi Gao, Xinquan Chen +3
The ability of humans to rapidly learn new knowledge while retaining old memories poses a significant challenge for current deep learning models. To handle this challenge, we draw…
Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
Junqi Gao, Biqing Qi, Yao Li +4
The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to tr…
Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
Biqing Qi, Pengfei Li, Fangyuan Li +3
Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the nee…
Enhancing Adversarial Transferability via Information Bottleneck Constraints
Biqing Qi, Junqi Gao, Jianxing Liu +2
From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advan…
SMR: State Memory Replay for Long Sequence Modeling
Biqing Qi, Junqi Gao, Kaiyan Zhang +4
Despite the promising performance of state space models (SSMs) in long sequence modeling, limitations still exist. Advanced SSMs like S5 and S6 (Mamba) in addressing non-uniform sa…
Exploring Adversarial Robustness of Deep State Space Models
Biqing Qi, Yang Luo, Junqi Gao +4
Deep State Space Models (SSMs) have proven effective in numerous task scenarios but face significant security challenges due to Adversarial Perturbations (APs) in real-world deploy…
Interactive Continual Learning: Fast and Slow Thinking
Biqing Qi, Xingquan Chen, Junqi Gao +4
Advanced life forms, sustained by the synergistic interaction of neural cognitive mechanisms, continually acquire and transfer knowledge throughout their lifespan. In contrast, con…
Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning
Biqing Qi, Junqi Gao, Xingquan Chen +4
Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounte…
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
Biqing Qi, Junqi Gao, Yiang Luo +3
The rise of generative neural networks has triggered an increased demand for intellectual property (IP) protection in generated content. Deep watermarking techniques, recognized fo…