Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
2
Batching future MH proposals unlocks significant speedups for LLM power sampling without altering the core reasoning process.
A novel inference-time sampling strategy unlocks frontier LLM reasoning capabilities in smaller models by resolving the exploration-exploitation dilemma.
Jointly pruning and quantizing weights under a single Bayesian objective breaks the traditional trade-offs of sequential compression pipelines, squeezing modern LLMs like Llama 3.2 and Qwen 2.5 further without catastrophic accuracy degradation.