Boxuan Lai

bxlai's activity

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

upvoted a paper about 5 hours ago

Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models

Paper • 2610.31569 • Published 6 days ago • 12

upvoted a paper about 20 hours ago

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

Paper • 2610.31062 • Published 6 days ago • 32

upvoted a paper 2 days ago

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 8 days ago • 657

upvoted a paper 3 days ago

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 9 days ago • 184

upvoted 2 papers 4 days ago

Cache Engineering for Agents

Paper • 2610.28577 • Published 8 days ago • 160

Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

Paper • 2610.17860 • Published 15 days ago • 51

upvoted a paper 5 days ago

SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration

Paper • 2610.26837 • Published 9 days ago • 29

upvoted 2 papers 6 days ago

DLite: History-free Speculative Decoding for Agentic AI

Paper • 2610.23787 • Published 12 days ago • 36

Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics

Paper • 2610.22169 • Published 13 days ago • 55

upvoted 3 papers 7 days ago

Velox: Spatial Memory Makes World Models Efficient

Paper • 2610.22311 • Published 13 days ago • 39

Virtual Head Attention

Paper • 2610.17959 • Published 15 days ago • 25

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Paper • 2610.22200 • Published 13 days ago • 107

upvoted 2 papers 8 days ago

History Replays Itself: Unleashing Long-Context Capability in Linear Attention

Paper • 2610.15715 • Published 17 days ago • 26

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Paper • 2610.14448 • Published 18 days ago • 49

upvoted a paper 9 days ago

QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation

Paper • 2610.10497 • Published 21 days ago • 19

upvoted a paper 10 days ago

Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

Paper • 2610.17656 • Published 15 days ago • 29

upvoted a paper 11 days ago

CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction

Paper • 2610.16577 • Published 16 days ago • 36

upvoted a paper 12 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 28 days ago • 150

upvoted 2 papers 13 days ago

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

Paper • 2610.12582 • Published 20 days ago • 19

Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models

Paper • 2610.08966 • Published 20 days ago • 27