1 citations · 2 across the 8 of their papers we have counts for
9 papers
Position: Agentic Evolution is the Path to Evolving LLMs
Minhua Lin, Hanqing Lu, Zhan Shi +11
As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with con…
TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Models
Zhizhao Luo, Zhaojing Luo, Meihui Zhang +1
Large language models (LLMs) have emerged as powerful tools for natural language table reasoning, where there are two main categories of methods. Prompt-based approaches rely on la…
Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
Omer Faruk Deniz, Ruiyu Mao, Ruochen Li +2
Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either be…
MAXS: Meta-Adaptive Exploration with LLM Agents
Jian Zhang, Zhiyuan Wang, Zhangqi Wang +7
Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer f…
See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
Zongru Wu, Rui Mao, Zhiyuan Tian +7
The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably…
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
Qi Wang, Yanrui Yu, Ye Yuan +2
Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nev…
Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions
Wentai Wu, Ligang He, Saiqin Long +4
Increasing legislation and regulations on private and proprietary information results in scattered data sources also known as the "data islands". Although Federated Learning-based…
AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
Xiaobao Wu, Liangming Pan, Yuxi Xie +7
Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly co…
Can a large language model be a gaslighter?
Wei Li, Luyao Zhu, Yang Song +3
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating langu…