Qwen/Qwen3.8-27B
类型 image-text-to-text · 框架 transformers · 下载 6,454,419 · 收藏 20,809
Hugging Face 上的模型、数据集与应用,带点赞与收录信息,适合追踪模型生态的最新发布。
类型 image-text-to-text · 框架 transformers · 下载 6,454,419 · 收藏 20,809
可直接在线体验的 HuggingFace Space(收藏 16,604),不用装环境就能跑。
类型 audio-to-audio · 下载 7,323 · 收藏 5,479
类型 image-text-to-text · 框架 peft · 下载 1,874 · 收藏 864
类型 image-text-to-text · 框架 transformers · 下载 136 · 收藏 645
类型 image-text-to-text · 收藏 204
End-to-end autonomous driving increasingly depends on scaling training demonstrations, yet data growth does not guarante…
Image vectorization reconstructs raster images as compact scalable vector graph- ics (SVG), providing a structured and e…
Experimentation teams must decide which proposed website changes to test with live traffic. We evaluated whether forecas…
Reinforcement learning (RL) post-training substantially improves the visual quality, text rendering, and compositional a…
Vision-language-action (VLA) models enable robots to perform diverse tasks from visual observations and language instruc…
类型 image-text-to-text · 框架 transformers · 下载 2,053 · 收藏 350
类型 text-to-video · 收藏 340
类型 audio-to-audio · 框架 inworld-voice-isolation · 收藏 276
Language models acquire their capabilities from training data, and developers withhold data during training to keep mode…
Frontier post-training follows a common recipe: train one expert per domain with reinforcement learning (RL), then conso…
In this paper, we propose a Unified Law for Visual Tasks, which could be further divided into Four Laws of Computer Visi…
AI agents are increasingly equipped with persistence toward task completion to run delegated work autonomously for long …
Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to req…
可直接在线体验的 HuggingFace Space(收藏 14,164),不用装环境就能跑。
类型 image-to-video · 框架 diffusion-single-file · 下载 2,789,021 · 收藏 12,240
类型 text-generation · 框架 transformers · 下载 29,567 · 收藏 8,795
类型 text-to-image · 框架 minimax-h3 · 下载 609,130 · 收藏 1,318
类型 text-to-image · 框架 diffusion-single-file · 下载 2,294,065 · 收藏 488
Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe dive…
Language moved from many task-specific models to one unified model: a single generative model with a single generative t…
Given a set of LEGO parts and an image of an assembled object, our task is to infer the pose of each part to assemble th…
Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations …
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compressi…
Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM,…
Reference-frame stabilization registers every frame of a hovering-drone video onto one reference frame, keeping object p…
Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated age…
类型 text-generation · 下载 5,545 · 收藏 558
类型 image-to-3d · 框架 idol · 下载 29,904 · 收藏 2,235
Which representation should be probed in a transformer-based foundation model? Recent work shows that the standard pract…
AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provision…
Subliminal learning is a phenomenon in large language models (LLMs) where a teacher passes a hidden preference to a stud…
We present FAME-QP, a GPU-accelerated solver for dense quadratic programs arising in linear model predictive control. FA…
类型 image-text-to-text · 框架 transformers · 下载 30,721 · 收藏 1,867
下载 6,480 · 收藏 487
Lloyd's k-means algorithm is a long-running standard for clustering, with applications in data analysis, retrieval, quan…
Large language models can generate motion graphics from static images and natural language requests, but it remains diff…
Small multimodal models can misjudge emotion when words, voice, and visual cues conflict. We present EmoHarness, which r…
In this work, we study whether frontier agent can continually improve real-world AI infrastructure over long horizons. W…
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric e…
Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, w…
Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recove…
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to acti…
We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a rad…
Industrial recommender systems allocate substantial computation to pointwise candidate scoring, yet separate reranking a…
Scientific names increasingly connect papers from different research topics, leaving readers to recover a paper's identi…
We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regressio…
可直接在线体验的 HuggingFace Space(收藏 11,315),不用装环境就能跑。
下载 221,506 · 收藏 877
Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text a…
Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long…
A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text r…
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iterati…
Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collec…
框架 minimax-h3 · 下载 950 · 收藏 395
下载 9,066 · 收藏 373
类型 image-text-to-text · 框架 transformers · 下载 9,592 · 收藏 1,615
类型 image-to-video · 框架 diffusers · 下载 863 · 收藏 474
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only …
A frontier AI model is trained in an AI data center, on tens of thousands of accelerators joined by a dedicated network,…
Streaming digital humans produce detailed video while continuing speech as new text arrives. High-resolution denoising i…
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the c…
Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated tar…
类型 image-text-to-text · 框架 transformers · 下载 221,621 · 收藏 5,270
类型 automatic-speech-recognition · 框架 nemo · 下载 44,939 · 收藏 1,489
类型 text-generation · 框架 transformers · 下载 54,959 · 收藏 1,485
Anticipating financial outcomes requires synthesizing evolving evidence and reasoning under uncertainty, making deep res…
Reinforcement learning (RL) has shown promise for training multimodal agents to reason and use tools. However, it remain…
With model weights fixed, we measure how much of an entity-replacement response transfers between English factual questi…
Missing modality imputation aims to synthesize unobserved modalities from observed ones. Existing methods treat each mod…
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors ca…
Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that …
Streaming video LLMs can now commentate live gameplay, but they are trained and tested on the same games. We study cross…
Few-step autoregressive video diffusion enables efficient generation, yet maintaining consistency over long rollouts rem…
Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes th…
On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. Thes…
类型 image-text-to-text · 框架 transformers · 下载 147,588 · 收藏 562
Perceiving human body motion is critical for multimodal systems that understand and assist people. Yet current evaluatio…
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction wi…
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training examp…
Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known? We g…
Federated learning (FL) keeps raw data local, but most deployments still rely on a trusted coordinator for client admiss…
类型 text-generation · 框架 transformers · 下载 15,795 · 收藏 971
Developers download quantized large language models (LLMs) from public registries to run them locally. None of the regis…
Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that p…
Language agents increasingly act through external tools and interactive environments, making the interface between the m…
Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, com…
Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-…
类型 text-generation · 框架 gguf · 下载 1,747,945 · 收藏 507
类型 text-generation · 框架 transformers · 下载 16,598 · 收藏 1,244
类型 text-generation · 框架 transformers · 下载 10,163 · 收藏 908
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading a…
Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning para…
The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that …
GUI grounding requires locating small controls in cluttered screenshots and identifying which control a natural-language…
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, ad…
类型 image-text-to-text · 框架 transformers · 下载 13,247 · 收藏 455
Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human le…
Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizi…
This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion …
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Y…
Phenomena responsible for emerging technologies originate from novel molecular states at buried interfaces. Yet quantita…
类型 image-to-image · 框架 diffusion-single-file · 下载 750,694 · 收藏 1,865
Energy-based models have shown promising properties for domain-specific tasks but remain challenging in modeling general…
Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent e…
Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achievin…
Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-drive…
Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy perfo…
Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diver…
Biometric authentication systems increasingly use privacy-preserving mechanisms to protect sensitive templates. However,…
Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely exami…
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide…
When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions? For solving lon…
Robots must act under physical and social constraints while adapting to changes in their environment and human needs. Ex…
Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconst…
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeat…
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passe…
Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process. In t…
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models…
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are ph…
Slider-based control aims to give users continuous, fine-grained control over the intensity of individual edits in instr…
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remai…
Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. E…
类型 text-to-image · 框架 diffusers · 下载 10,757 · 收藏 711