SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Modelsby Jiale Cheng, Xiao…
Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentationby Svetlana Pavlitska, Enrico Eisen, J.…
QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Modelsby Changhai Zhou, Yuhua Zhou,…
EvoLlama: Enhancing LLMs’ Understanding of Proteins via Multimodal Structure and Sequence Representationsby Nuowei Liu, Changzhi…
A Mapper Algorithm with implicit intervals and its optimizationby Yuyang Tao, Shufei GeFirst submitted to…
BA-BFL: Barycentric Aggregation for Bayesian Federated Learningby Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios…
Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptationby Wei Chen,…
CNNtention: Can CNNs do better with Attention?by Nikhil Kapila, Julian Glattki, Tejas RathiFirst submitted to…
C3oT: Generating Shorter Chain-of-Thought without Compromising Effectivenessby Yu Kang, Xianghui Sun, Liangyu Chen, Wei ZouFirst…
Non-Convex Optimization in Federated Learning via Variance Reduction and Adaptive Learningby Dipanwita Thakur, Antonella Guzzo,…