EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolantsby Allan dos Santos Costa, Ilan Mitnikov, Franco…
MoIN: Mixture of Introvert Experts to Upcycle an LLMby Ajinkya Tejankar, KL Navaneet, Ujjawal Panchal,…
ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flawsby Hai Huang, Randall BalestrieroFirst submitted to arxiv…
CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Deviceby Yicheng Fu, Raviteja Anantha,…
Towards the Effect of Examples on In-Context Learning: A Theoretical Case Studyby Pengfei He, Yingqian…
C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Setsby Kangdao Liu, Hao Zeng, Jianguo Huang,…
MTL-LoRA: Low-Rank Adaptation for Multi-Task Learningby Yaming Yang, Dilxat Muhtar, Yelong Shen, Yuefeng Zhan, Jianfeng…
FlatQuant: Flatness Matters for LLM Quantizationby Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang…
Skipping Computations in Multimodal LLMsby Mustafa Shukor, Matthieu CordFirst submitted to arxiv on: 12 Oct…
VERITAS-NLI : Validation and Extraction of Reliable Information Through Automated Scraping and Natural Language Inferenceby…