Submitted by pmolchanov 58 LLM Pruning and Distillation in Practice: The Minitron Approach · 9 authors 4
Submitted by akhaliq 56 TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models · 21 authors 2
Submitted by akhaliq 18 TrackGo: A Flexible and Efficient Method for Controllable Video Generation · 7 authors 2
Submitted by jonathan-roberts1 9 GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models · 3 authors 2
Submitted by LiyaoJiang 7 FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting · 7 authors 2
Submitted by amanchadha 6 Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification · 5 authors 4
Submitted by Idan 6 Iterative Object Count Optimization for Text-to-image Diffusion Models · 3 authors 2
Submitted by akhaliq 6 Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation · 5 authors 2
Submitted by NiccoBiondi 6 Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer · 4 authors 2
Submitted by amanchadha 5 Unboxing Occupational Bias: Grounded Debiasing LLMs with U.S. Labor Data · 3 authors 4
Submitted by IAMJB 4 Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation · 3 authors 1