153 citations · 333 across the 85 of their papers we have counts for
91 papers
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Qingchuan Ma, Yuexiao Ma, Xiang Meng +7
Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, a…
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue
Chengqian Ma, Wenhao Feng, Weixuan Jin +7
Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries. Existing benchmarks evaluate turn-taking, interruption ha…
CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents
Weizhong Huang, Jinchao Zhang, Xiawu Zheng
Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations. Their key-value (KV) caches grow accordingly, increasing…
YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family
Xu Lin, WenJie Nie, Jinlong Peng +4
Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous operators and detection-specif…
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
Wang Chen, Yu Chen, Xiang Wang +3
Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Since the appropriate frame budg…
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
Yuhui Zeng, Wang Chen, Jinfa Huang +5
Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods a…
TimePLE: Rethinking Temporal Representation for Video Temporal Grounding
Yuhui Zeng, Xinyu Mao, Xiaokun Liu +4
Video temporal grounding (VTG) aims to localize the continuous video interval described by a natural-language query. However, current VLM-based methods typically produce this inter…
Toward Robust In-Context Segmentation via Concept Guidance
Zhigang Chen, Xiawu Zheng, Rongrong Ji
In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding masks, without updating any para…
OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping
Xudong Li, Mengdan Zhang, Peixian Chen +7
Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognit…
Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
Yigeng Jiang, Tengchao Yang, Taoyong Cui +25
Deep research agents are Large Language Model (LLM)-based systems designed for autonomous, multi-step scientific reasoning, and they hold immense potential for accelerating researc…
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
Wanqi Yang, Yuexiao Ma, Alexander Conzelmann +4
Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in me…
A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
Qingchuan Ma, Yuexiao Ma, Yongkang Xie +3
Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measuring this ability remains cha…
Motion-Aware Caching for Efficient Autoregressive Video Generation
Jing Xu, Yuexiao Ma, Xuzhe Zheng +7
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential i…
ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization
Kunpeng Liao, Yuexiao Ma, Yisheng Lin +3
Algorithm Visualization (AV) helps students build mental models by animating algorithm execution states. Recent LLM-based systems such as CODE2VIDEO generate AV videos in an end-to…
HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion
Xuzhe Zheng, Yuexiao Ma, Jing Xu +3
Sparse attention accelerates video diffusion by allowing each attention head to focus on only a small subset of interactions. Existing methods already construct head-specific spars…
Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement
Xudong Li, Jiaxi Tan, Ziyin Zhou +6
Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores b…
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Chaoyou Fu, Haozhi Yuan, Yuhao Dong +16
With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and…
Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Wang Chen, Yuhui Zeng, Yongdong Luo +5
Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically sel…
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Haoyu Huang, Jinfa Huang, Zhongwei Wan +3
Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. How…
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
Tianyu Xie, Jinfa Huang, Yuexiao Ma +11
Evaluating omni-modal large language models (OLMs) in multi-party dialogue requires more than answer correctness on pre-segmented inputs. We introduce SocialOmni, an offline diagno…
Event-Anchored Frame Selection for Effective Long-Video Understanding
Wang Chen, Yongdong Luo, Yuhui Zeng +5
Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approa…
Flow caching for autoregressive video generation
Yuexiao Ma, Xuzhe Zheng, Jing Xu +9
Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. Howeve…
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
Cheng Yang, Haiyuan Wan, Yiran Peng +8
Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reaso…
Polybasic Speculative Decoding Through a Theoretical Perspective
Ruilin Wang, Huixia Li, Yuexiao Ma +4
Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in acceler…