Submitted by Hitesh Kandala 3 DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference AMD 14 2
Submitted by Prakamya Mishra 5 Instella: Fully Open Language Models with Stellar Performance AMD 317 2
Submitted by Prakamya Mishra 7 SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers AMD 1 2
Submitted by Prakamya Mishra - TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games AMD 2