Submitted by akhaliq 47 Specialized Language Models with Cheap Inference from Limited Domain Data · 4 authors 2
Submitted by akhaliq 43 StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback · 16 authors 74 3
Submitted by akhaliq 38 TravelPlanner: A Benchmark for Real-World Planning with Language Agents · 8 authors 483 2
Submitted by akhaliq 32 PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models · 3 authors 198 3
Submitted by akhaliq 27 Boximator: Generating Rich and Controllable Motions for Video Synthesis · 7 authors 4
Submitted by akhaliq 24 Repeat After Me: Transformers are Better than State Space Models at Copying · 4 authors 36 4
Submitted by akhaliq 15 Nomic Embed: Training a Reproducible Long Context Text Embedder · 4 authors 1
Submitted by akhaliq 14 EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks · 3 authors 2