2 citations · 10 across the 45 of their papers we have counts for
48 papers
Behavior Pack Optimization for Video MLLM Post-Training
Zhaolu Kang, Shiyu Liu, Tailong Luo +12
Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that supports the answer, or occludi…
Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression
Jingbo Wen, Liang He, Mingyu Cao +4
Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed…
Agents-K1: Towards Agent-native Knowledge Orchestration
Zongsheng Cao, Bihao Zhan, Jinxin Shi +25
Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstract…
Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
Qianjun Pan, Yutao Yang, Junsong Li +5
Retrieval-augmented generation (RAG) enables agents to access external knowledge at inference time, but it primarily retrieves fragmented declarative evidence, leaving agents to re…
MemPro: Agentic Memory Systems as Evolvable Programs
Qingshan Liu, Guoqing Wang, Wen Wu +5
Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing…
BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
Liang He, Jingbo Wen, Qishi Zhan +4
Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel. In resource-constrained deployments, the…
Can Heterogeneous Language Models Be Fused?
Shilian Chen, Jie Zhou, Qin Chen +4
Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Rece…
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
Jie Zhou, Qin Chen, Liang He
Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They…
From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
Shihao Zhang, Ziwei Wang, Jie Zhou +6
While Aspect-based Sentiment Analysis (ABSA) systems have achieved high accuracy in identifying sentiment polarities, they often operate as "black boxes," lacking the explicit reas…
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
Yuxuan Cai, Wei Li, Jie Zhou +4
Online lifelong learning agents must decide not only how to act but also when to consult prior experience to continually improve on long-horizon tasks. Existing methods typically r…
PRMB: Benchmarking Reward Models in Long-Horizon CBT-based Counseling Dialogue
Yougen Zhou, Qin Chen, Ningning Zhou +2
Large language models (LLMs) hold potential for mental healthcare applications, particularly in cognitive behavioral therapy (CBT)-based counseling, where reward models play a crit…
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Jianghao Yin, Qin Chen, Kedi Chen +3
Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation…
PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor
Qianjun Pan, Junyi Wang, Jie Zhou +10
To develop a reliable AI for psychological assessment, we introduce \texttt{PsychEval}, a multi-session, multi-therapy, and highly realistic benchmark designed to address three key…
Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding
Jianghao Yin, Qingbin Li, Kun Sun +10
While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image…
Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
Kedi Chen, Zhikai Lei, Xu Guo +10
Large language models (LLMs) make remarkable progress in reasoning tasks. Among different reasoning modes, inductive reasoning, due to its better alignment with human learning, att…
A Survey of Inductive Reasoning for Large Language Models
Kedi Chen, Dezhao Ruan, Yuhao Dan +12
Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by i…
Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Shilian Chen, Jie Zhou, Tianyu Huai +9
Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models…
Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations
Yougen Zhou, Qin Chen, Ningning Zhou +3
Emotional support conversation (ESC) aims to alleviate distress through empathetic dialogue, yet large language models (LLMs) face persistent challenges in delivering effective ESC…
DiaCBT: A Long-Periodic Dialogue Corpus Guided by Cognitive Conceptualization Diagram for CBT-based Psychological Counseling
Yougen Zhou, Ningning Zhou, Qin Chen +3
Psychotherapy reaches only a small fraction of individuals suffering from mental disorders due to social stigma and the limited availability of therapists. Large language models (L…
LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
Junsong Li, Jie Zhou, Bihao Zhan +7
Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic…
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li +9
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. T…
Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
Yuxuan Cai, Yipeng Hao, Jie Zhou +14
As AI advances toward general intelligence, the focus is shifting from systems optimized for static tasks to creating open-ended agents that learn continuously. In this paper, we i…
Protein-SE(3): Benchmarking SE(3)-based Generative Models for Protein Structure Design
Lang Yu, Zhangyang Gao, Cheng Tan +3
SE(3)-based generative models have shown great promise in protein geometry modeling and effective structure design. However, the field currently lacks a modularized benchmark to en…
Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
Linhao Ye, Lang Yu, Zhikai Lei +3
Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step re…