HuggingFace
Evaluating the Hidden Costs of Personalization in Large Language Models
While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, the...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models
Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant be...
HuggingFace
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Organizations often develop and maintain portfolios of related applications: independently deployable codebases that ...
HuggingFace
Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models
Recent work on image content manipulation based on vision-language pre-training models has been effectively extended ...
HuggingFace
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual...
HuggingFace
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing e...
HuggingFace
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are sti...
HuggingFace
Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors
Extractive prompt compression promises to cut LLM inference costs by removing low-information tokens, and learned com...
HuggingFace
Sliding-window beats linear attention
Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new ...
HuggingFace
Generative Semantic Scene Completion
Outdoor LiDAR semantic scene completion (SSC) recovers a dense semantic voxel grid from a scan observing 1% of the ta...
HuggingFace
EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. S...
HuggingFace
Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state ...