Barry Li

Brilliant-B's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 10 days ago

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Paper • 2606.15956 • Published 13 days ago • 12

upvoted a paper 14 days ago

MiniMax Sparse Attention

Paper • 2606.13392 • Published 16 days ago • 148

upvoted 4 papers 17 days ago

Latent Spatial Memory for Video World Models

Paper • 2606.09828 • Published 19 days ago • 71

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Paper • 2606.09079 • Published 19 days ago • 64

Agents' Last Exam

Paper • 2606.05405 • Published 24 days ago • 366

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published 22 days ago • 75

liked a model 24 days ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 5 days ago • 1.75M • • 5.08k

upvoted 4 papers 24 days ago

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models

Paper • 2605.28132 • Published May 27 • 25

ESPO: Early-Stopping Proximal Policy Optimization

Paper • 2605.29860 • Published about 1 month ago • 20

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Paper • 2605.30351 • Published about 1 month ago • 26

NITP: Next Implicit Token Prediction for LLM Pre-training

Paper • 2605.24956 • Published May 24 • 35

upvoted 3 papers 29 days ago

Rethinking Memory as Continuously Evolving Connectivity

Paper • 2605.28773 • Published May 27 • 34

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 75

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Paper • 2605.30280 • Published about 1 month ago • 146

upvoted 6 papers about 1 month ago

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 144

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Paper • 2605.27366 • Published May 26 • 29

Toward Native Multimodal Modeling: A Roadmap

Paper • 2605.25343 • Published May 25 • 43

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published May 16 • 97

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20, 2025 • 73

Streaming Video Instruction Tuning

Paper • 2512.21334 • Published Dec 24, 2025 • 11