Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 193
caohaoyu
rechy
·
AI & ML interests
None yet
Recent Activity
authored a paper about 9 hours ago
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding authored a paper about 9 hours ago
When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition authored a paper about 9 hours ago
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete DiffusionOrganizations
None yet
authored 5
papers about 9 hours ago
When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
Paper • 2603.16256 • Published • 1
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper • 2603.06577 • Published • 48
DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model
Paper • 2512.12633 • Published
RISE-Video: Can Video Generators Decode Implicit World Rules?
Paper • 2602.05986 • Published • 26
authored 12
papers 2 months ago
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
Paper • 2309.01131 • Published • 1
Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
Paper • 2402.19014 • Published
Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction
Paper • 2406.12707 • Published
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy
Paper • 2502.05177 • Published • 2
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Paper • 2505.03739 • Published • 9
VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Paper • 2510.09607 • Published • 2
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
Paper • 2510.21817 • Published • 41
Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts
Paper • 2510.16448 • Published
TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs
Paper • 2505.20777 • Published
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
Paper • 2601.19798 • Published • 43
BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
Paper • 2508.06895 • Published
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
Paper • 2601.20430 • Published • 16