HuggingFace

Articles from HuggingFace

Cards List

Hugging Face and OpenRouter join forces to make open-weight models easy to run

Hugging Face Blog ↗ · yesterday Cached

Hugging Face is switching its Inference Providers from a custom router to OpenRouter, letting any open-weight model on the Hub be called via a single Hugging Face token with automatic provider selection based on price, speed, and reliability.

0 favorites 0 likes

n4ze3m/tiny-voca

Hugging Face Models Trending ↗ · 2d ago Cached

tiny-voca 是一个仅 4.5M 参数的轻量英文文本转语音模型,包含两个美式英语音色,在四线程 CPU 上运行速度约为实时的 70 倍,提供 PyTorch 与 ONNX 权重、代码及浏览器试用空间。

0 favorites 0 likes

Build a Robot Pick-and-Place Simulation with SimReady Assets

Hugging Face Blog ↗ · 3d ago Cached

A walkthrough showing how to build a robot pick-and-place simulation in Isaac Sim using NVIDIA's SimReady OpenUSD assets, including the UR17G arm, Robotiq 2F-140 gripper, and a beverage can asset from the SimReady Central library on Hugging Face.

0 favorites 0 likes

XYBench: Helping with the problem behind the question

Hugging Face Blog ↗ · 3d ago Cached

AllenAI and collaborators release XYBench, an 8K+ question benchmark (Best Resource Paper at EMNLP 2026) that tests whether AI assistants recognize when a user's request is based on the XY problem misconception and redirect toward the actual goal. Evaluations of Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro show models still focus on the mistaken approach rather than steering users to the underlying goal.

0 favorites 0 likes

llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem

Hugging Face Blog ↗ · 3d ago Cached

llama.cpp releases v1.0.0 of its libraries, establishing a stable API/ABI foundation with strict semantic versioning for the local AI ecosystem, plus expanded distribution channels and CI infrastructure.

0 favorites 0 likes

DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery

Hugging Face Daily Papers ↗ · 4d ago Cached

DySENSE is a joint multimodal GenAI framework that synthesizes static urban satellite imagery alongside spatially aligned, dynamic monthly building energy consumption maps, decoupling long-term urban morphology from short-term energy dynamics. Evaluated on four cities, it achieves strong downstream performance with less than 25% labeled data.

0 favorites 0 likes

OneSteer: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control

Hugging Face Daily Papers ↗ · 4d ago Cached

OneSteer is a one-step diffusion whole-body controller that combines general humanoid motion tracking with selective test-time steering via differentiable task costs and reference masks, achieving a 90% clean passage rate under a 1.25m bar (up from 2%) and completing 27/27 nominal tracking trials on a physical Unitree G1 without falling.

0 favorites 0 likes

Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift

Hugging Face Daily Papers ↗ · 4d ago Cached

该论文评测了73种无参考图像质量评估指标与人类偏好的一致性,发现没有指标能稳定匹配人类判断,并提出了包含人类参考、编辑、对抗攻击与生成式漂移图像的基准TrustUIQA。

0 favorites 0 likes

V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned Representations

Hugging Face Daily Papers ↗ · 4d ago Cached

V-JEPA-LM introduces open video-language models combining a frozen V-JEPA 2.1 world-model encoder with Qwen3/Llama backbones, trained in one stage with counterfactual supervision that forces models to reason about dynamics rather than static text-aligned features, leading all size classes on 11 video benchmarks with far less data and fewer visual tokens than Meta's V-JEPA 2/2.1 video LLMs.

0 favorites 0 likes

Envisioning Agentic Robotics: A New Era of Robotic Systems

Hugging Face Daily Papers ↗ · 4d ago Cached

This paper introduces 'agentic robotics' as a new paradigm where a foundation model paired with an embodied harness forms an 'Embodied System 2' for open-world physical tasks, and proposes an evaluation framework plus a research roadmap toward sustained autonomy.

0 favorites 0 likes

AI Reviews Are Biased Towards the Appendix

Hugging Face Daily Papers ↗ · 4d ago Cached

研究分析了 ACL、EMNLP、COLM 和 ICLR 的 2000 篇论文,发现 GPT 和 Claude 等大模型在审稿中约一半以上的批评点来自附录,而人类审稿人仅有 8.4%,且更关注论文呈现与核心思想。

0 favorites 0 likes

MEM-SQL: Memory-Empowered Text-to-SQL

Hugging Face Daily Papers ↗ · 4d ago Cached

The paper introduces HARE, a history-aware Text-to-SQL benchmark, and MEM-SQL, a memory-powered method that reuses verified SQL templates and blocks with on-demand schema linking, raising mean execution accuracy from 37.1% to 50.0% across six language models while cutting input tokens by 76.6% and latency by 68.8%.

0 favorites 0 likes

CANTraj: Recovering Vehicle Trajectories from CAN Signals in Naturalistic Driving

Hugging Face Daily Papers ↗ · 4d ago Cached

CANTraj releases a naturalistic driving dataset and benchmark for recovering vehicle trajectories from CAN signals without GPS, showing that combining steering signals with road-network constraints raises five-minute route recovery from 56% to 87%, and that an LLM harness further improves candidate route selection.

0 favorites 0 likes

Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent

Hugging Face Daily Papers ↗ · 4d ago Cached

miHoYo's Honkai AI R&D team introduces Gamer, a generalist Vision-Language-Action foundation model that plays long-horizon 3D games in real time via screenshots, keyboard, and mouse—using 10K+ hours of gameplay data, a Streaming-vLLM inference engine with 20× lower latency, and Temporal-Aware GRPO for hour-long RL training, handling over 95% of Honkai: Star Rail's main story challenges.

0 favorites 0 likes

JVT: Just Video Transformer makes pixel-space video diffusion simple

Hugging Face Daily Papers ↗ · 4d ago Cached

The paper introduces JVT (Just Video Transformer), a simple large-patch DiT-style Transformer that enables pixel-space video diffusion without pretrained autoencoders or U-Net skip connections, achieving quality competitive with latent diffusion baselines and supporting joint camera-conditioned RGB-disparity generation.

0 favorites 0 likes

eDIAR: Training-Free Open-Speaker Streaming Diarization for Long Meetings and Large Archives via e-means

Hugging Face Daily Papers ↗ · 4d ago Cached

eDIAR proposes a training-free, open-speaker streaming diarization method that removes fixed speaker-slot limits by clustering speaker embeddings with the e-means algorithm, achieving better accuracy on long meetings than Streaming Sortformer with constant per-update cost.

0 favorites 0 likes

JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams

Hugging Face Daily Papers ↗ · 4d ago Cached

JFinBench introduces a continuously refreshable Japanese financial benchmark of 321 examples drawn from 2026 certification exams, built via a human-in-the-loop agentic pipeline to mitigate data contamination. Evaluating 12 LLMs, Claude Fable5 and GPT-6 Astra exceed 93%, while the best open-weight model Kimi K3.1 Pro trails by 12 points, with tool access narrowing but not closing the gap.

0 favorites 0 likes

MMFlash: Faster Speculative Decoding for Vision-Language Models

Hugging Face Daily Papers ↗ · 4d ago Cached

MMFlash improves multimodal speculative decoding by adaptively upweighting visually dependent tokens and using sparse attention for long video inputs, achieving up to 3.58× lossless decoding speedup and outperforming EAGLE-3 and DFlash.

0 favorites 0 likes

LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

Hugging Face Blog ↗ · 4d ago Cached

IBM releases LLMON, an LLM-native markup language, along with two experimental Granite 4.1 3B and 8B preview models trained to consume and generate LLMON-marked text, improving structure handling and nearly eliminating indirect prompt injection attacks.

0 favorites 0 likes

higurashi-ai/Haru-4B

Hugging Face Models Trending ↗ · 4d ago Cached

Haru-4B is a low-latency, multilingual full-duplex continuous spoken dialogue foundation model that listens and speaks simultaneously at 7.5 Hz, using a Qwen3.5-4B backbone with a MeanFlow audio head for one-step continuous audio generation. It is released as a research base model with PyTorch, MLX, and vLLM-Omni implementations.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback