On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhancement, and model compression. However, OPD…
HUGGINGFACE PAPERS
We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an…
HUGGINGFACE PAPERS
Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one…
HUGGINGFACE PAPERS
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can generate concrete visual rollouts of possible…
HUGGINGFACE PAPERS
Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent…
HUGGINGFACE PAPERS
We propose Decoupled Residual Denoising Diffusion models (DRDD) for unified and data-efficient image-to-image (I2I) translation. While diffusion models have advanced I2I translation in terms of quality and diversity, we…
HUGGINGFACE PAPERS
Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer…
HUGGINGFACE PAPERS
Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limiting their ability to interact with…
HUGGINGFACE PAPERS
Instruction tuning aligns large language models, including multimodal ones, with diverse user intents, but scaling to heterogeneous mixtures is hindered by gradient interference and bandwidth-heavy synchronization. We…
HUGGINGFACE PAPERS
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs). Despite…
HUGGINGFACE PAPERS
Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existing adaptive sampling methods partially mitigate this issue by…
HUGGINGFACE PAPERS
Affordance understanding bridges visual perception and physical action, serving as an explainable interface for robot manipulation in open and unstructured real-world environments. Yet, building an affordance foundation…
HUGGINGFACE PAPERS
Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by training a single model…
HUGGINGFACE PAPERS
Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of applications such as household service robotics, assistive robotics,…
HUGGINGFACE PAPERS
We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining errors concentrate in under-optimized…
HUGGINGFACE PAPERS
Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet answer-correct traces can still lead to markedly different fine-tuning outcomes. We study post-conclusion…
HUGGINGFACE PAPERS
Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible…
HUGGINGFACE PAPERS
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the…
HUGGINGFACE PAPERS
Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking is fundamental to video understanding,…
HUGGINGFACE PAPERS
True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under different conditions, and deciding what to do next. We refer to…
HUGGINGFACE PAPERS
Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction methods reduce this cost by evicting unimportant key-value pairs…
HUGGINGFACE PAPERS
Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited…
HUGGINGFACE PAPERS
Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub…
HUGGINGFACE PAPERS
Effective real-world assistance requires AI agents with robust Theory of Mind (ToM): inferring human mental states from their behavior. Despite recent advances, several key challenges remain, including (1) online…
HUGGINGFACE PAPERS
We present a novel formulation for mesh-free, reduced-order simulation of deformable hyperelastic objects. Existing work in reduced-order elastodynamic simulation represents the input geometry by either meshes, which…
HUGGINGFACE PAPERS
Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper…
HUGGINGFACE PAPERS
Research on AI-generated text detection has presented a number of approaches to discern human from AI prose, some of which achieving high in-distribution performance. However, real-world applicability has stalled…
HUGGINGFACE PAPERS
The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) architectures address this by decoupling…
HUGGINGFACE PAPERS
Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative…
HUGGINGFACE PAPERS