Good Papers

Showing papers from Sensetime (China) Show all papers

72%Highly rated
?Highly ratedVote to see the score
arXivNanyang TechnologicalBeihangSensetimeVision-language-action models

RealtimeWAM: One-Step Asynchronous World Action Models

RealtimeWAM uses teacher-anchored consistency distillation and cross-expert wavefront pipelining for one-step asynchronous action generation, achieving near-lossless performance with ~25x speedup.

Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong and 6 more

Published Oct 5, 2026 · ▲ 24 on Hugging Face · Code ★ 2,902

0% Readers
14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 14 of 20 reviewers recommend it
lenient 4/5
medium 9/10
strict 1/5
86%Must read
?Must readVote to see the score
AAAI 2026Nanyang TechnologicalBeihangSensetimeHong Kong University of Science Efficient inference & serving

LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit

LLMC+ benchmarks vision-language model compression via modular toolkit, showing spatial/temporal redundancies need distinct strategies, token reduction harms multi-turn dialogue, and combined compression achieves extreme ratios with minimal loss.

Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong and 6 more

Published Mar 14, 2026 · 0 citations · Code ★ 751

– Readers
14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 14 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 1/5