SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environmentsby…
Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learningby Hongyi Yuan, Suqi…
MoIN: Mixture of Introvert Experts to Upcycle an LLMby Ajinkya Tejankar, KL Navaneet, Ujjawal Panchal,…
CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Deviceby Yicheng Fu, Raviteja Anantha,…
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimizationby Kaixuan Ji, Guanlin Liu,…
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Modelsby Qin Liu, Chao Shang, Ling Liu,…
Language model developers should report train-test overlapby Andy K Zhang, Kevin Klyman, Yifan Mai, Yoav…
Bilinear MLPs enable weight-based mechanistic interpretabilityby Michael T. Pearce, Thomas Dooms, Alice Rigg, Jose M.…
HyperDPO: Conditioned One-Shot Multi-Objective Fine-Tuning Frameworkby Yinuo Ren, Tesi Xiao, Michael Shavlovsky, Lexing Ying, Holakou…
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented…