HuggingFace
ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains o...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete...
HuggingFace
How Good Can Linear Models Be for Time-Series Forecasting?
Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers ...
HuggingFace
The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring...
HuggingFace
MultiHashFormer: Hash-based Generative Language Models
Language models (LMs) represent tokens using embedding matrices that scale linearly with the vocabulary size. To cons...
HuggingFace
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Oper...
HuggingFace
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches,...
HuggingFace
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consisten...
HuggingFace
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
LLM-based code agents navigate repositories through keyword search but miss the structural relationships, such as cal...
HuggingFace
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing...
HuggingFace
The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models
Tokenization is central to adapting scientific data for transformer-based foundation models, yet its impact on learne...
HuggingFace
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
For agents to learn continuously from interaction with the world at test time, they must be able to explore effective...