1 citations · 2 across the 11 of their papers we have counts for
13 papers
ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning
Yuan Liu, Haoyue Peng, Fanliang Hu +2
Multi-agent Large Language Model (LLM) systems typically commit to a deliberation protocol before inference. A fixed protocol cannot allocate computation differently to resolved an…
Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models
Yuan Liu, Haoyue Peng, Fanliang Hu +2
Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. W…
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
Jiabin Lou, Haopeng Wang, Yuanshuai Wang +6
Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encode spatial priors, such as orie…
EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
Siwei Wen, Zhangcheng Wang, Xingjian Zhang +2
Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its fundamental challenge lies in t…
RLLaVA: An RL-central Framework for Language and Vision Assistants
Lei Zhao, Zihao Ma, Boyu Lin +3
We present an RL-central framework for Language and Vision Assistants (RLLaVA) with its formulation of Markov decision process (MDP). RLLaVA decouples RL algorithmic logic from mod…
What Color Is the Text? A Benchmark for Hallucination Induced by Image-Embedded Prompt
Jinkun Zhao, Lei Huang, Haixin Ge +1
We introduce Embedded Stroop, a controlled diagnostic paradigm for measuring image-embedded prompt interference in Multimodal Large Language Models (MLLMs), where the query is rend…
EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Xingjian Zhang, Siwei Wen, Wenjun Wu +1
Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO…
CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering
Jinkun Zhao, Yuanshuai Wang, Xingjian Zhang +6
With the rapid evolution of artificial intelligence, AIOps has emerged as a prominent paradigm in DevOps. Lots of work has been proposed to improve the performance of different AIO…
VoQA: Visual-only Question Answering
Jianing An, Luyang Jiang, Jie Luo +2
Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). Howev…
Parallel Layer Normalization for Universal Approximation
Yunhao Ni, Yuxin Guo, Yuhe Liu +4
Layer Normalization (LN) is usually studied for its role in optimization, but it also acts as a multivariate nonlinearity between affine layers. We investigate how grouping LN unit…
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Xingjian Zhang, Siwei Wen, Wenjun Wu +1
Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly…
TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler
Xingjian Zhang, Xi Weng, Yihao Yue +3
Video behavior recognition and scene understanding are fundamental tasks in multimodal intelligence, serving as critical building blocks for numerous real-world applications. Throu…
Bench-CoE: a Framework for Collaboration of Experts from Benchmark
Yuanshuai Wang, Xingjian Zhang, Jinkun Zhao +5
Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven ex…