2 citations · 9 across the 21 of their papers we have counts for
21 papers
Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents
Shudong Liu, Dongyang Chen, Enci Zhang +3
Evaluation is shifting from static QA toward agentic settings where models act through external tools. We identify a critical yet underexplored capability within this space - dexte…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
TAPO: Transition-Aware Policy Optimization for LLM Agents
Cong Li, Peixi Peng, Yisen Zhao +4
Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing methods predominantly rely on…
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
Kai Chen, Zichen Ding, Jiaye Ge +20
As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly…
Expectation Alignment of Language Models for Real-World User Expectations
Miaomiao Li, Yang Wang, Bin Liang +3
Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing…
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG
Guanhua Chen, Chuyue Huang, Yutong Yao +4
Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and…
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
Guanhua Chen, Yutong Yao, Shenghe Sun +5
Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA)…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
How Far Are We from Genuinely Useful Deep Research Agents?
Dingling Zhang, He Zhu, Jincheng Ren +15
Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRAs were validated on…
ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning
Hongwei Liu, Junnan Liu, Shudong Liu +33
The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Co…
How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
Zihan Ma, Dongsheng Zhu, Shudong Liu +6
Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within com…
Intern-S1: A Scientific Multimodal Foundation Model
Lei Bai, Zhongrui Cai, Yuhang Cao +173
In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that…
FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective
Zhekai Zhou, Shudong Liu, Zhaokun Zhou +4
Federated learning (FL) is a decentralized machine learning paradigm in which multiple clients collaboratively train a shared model without sharing their local private data. Howeve…
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Shudong Liu, Hongwei Liu, Junnan Liu +8
Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward m…
Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
Junnan Liu, Hongwei Liu, Linchen Xiao +5
We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning tra…
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Rui Wang, Hongru Wang, Boyang Xue +9
Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (Sy…
CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries
Shudong Liu, Yiqiao Jin, Cheng Li +6
Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in p…
Learning from "Silly" Questions Improves Large Language Models, But Only Slightly
Tingyuan Zhu, Shudong Liu, Yidong Wang +4
Constructing high-quality Supervised Fine-Tuning (SFT) datasets is critical for the training of large language models (LLMs). Recent studies have shown that using data from a speci…
Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
Zihao Zhou, Shudong Liu, Maizhen Ning +6
Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mat…
Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization
Chi Seng Cheang, Hou Pong Chan, Derek F. Wong +5
Recent pre-trained language models (PLMs) achieve promising results in existing abstractive summarization datasets. However, existing summarization benchmarks overlap in time with…
Deep learning based on mixed-variable physics informed neural network for solving fluid dynamics without simulation data
Guang-Tao Zhang, Chen Cheng, Shu-dong Liu +2
Deep learning method has attracted tremendous attention to handle fluid dynamics in recent years. However, the deep learning method requires much data to guarantee the generalizati…