Search papers, labs, and topics across Lattice.
Affiliation:
5
347
10
6
OnPanda is presented, an interactive tool for efficiently annotating LLM alignment data and agent trajectories that adopts token-level correction as its core interaction and releases Panda-CVL, a dataset annotated with onPanda, together with a benchmark for token-level correction.
Sparse prefilling can dramatically accelerate long-context inference in diffusion language models, achieving up to 28x speedup without sacrificing quality.
Text-based speculative decoding falls flat for vision-language models, but ViSkip dynamically adapts to vision tokens for state-of-the-art acceleration.
Forget complex RLHF pipelines: simple PPO with rule-based rewards can outperform state-of-the-art reasoning models while slashing training costs by 90%.
