AI研究論文每日精選

GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models

Iterative Object Count Optimization for Text-to-image Diffusion Models

FocusLLM: Scaling LLM's Context by Parallel Decoding

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models

TrackGo: A Flexible and Efficient Method for Controllable Video Generation

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer

Unboxing Occupational Bias: Grounded Debiasing LLMs with U.S. Labor Data

Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation

Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification

Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation

FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting

LLM Pruning and Distillation in Practice: The Minitron Approach