HuggingFace
An AI4AI Framework for Visual Token Pruning
Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet exi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, ...
HuggingFace
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recent...
HuggingFace
TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement
Extreme events in air transport, such as severe arrival delays and abnormal air times, cause cascading network disrup...
HuggingFace
PixSDS: Why Latent SDS Makes Noisy Pixels
Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffu...
HuggingFace
Parameter Exploration for RLVR via Variational Learning
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evi...
HuggingFace
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packag...
HuggingFace
Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning
The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely f...
HuggingFace
Gaze Target Estimation Anywhere with Concepts
Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primar...
HuggingFace
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inhere...
HuggingFace
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
Large language models often fail when answer options require combining atomic judgments under explicit logical operat...
arXiv
HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression
Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-...