HuggingFace
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, execut...
HuggingFace 来源
HuggingFace
Principia: Relational Physics Tests for Video Models
Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate,...
HuggingFace
Environment Evolution for Terminal Agents
Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become m...
HuggingFace
Editable Visual Design
While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-t...
HuggingFace
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing...
HuggingFace
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. E...
HuggingFace
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thoug...
HuggingFace
WorldReward: Reward Modeling for Camera-Conditioned World Models
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected sce...
HuggingFace
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera t...
HuggingFace
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation
Joint audio-video generation models have made substantial progress in visual quality and audio-visual synchronization...
HuggingFace
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs a...
HuggingFace
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation...
HuggingFace
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often ...
HuggingFace
PACE: Towards Surfacing Hidden Conflicts in User Requests
Personalized assistants should not only comply with user requests but also assess whether those requests are appropri...
HuggingFace
Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invar...
HuggingFace
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remot...
HuggingFace
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 p...
HuggingFace
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fi...
HuggingFace
Using Grounded Theory for Agent Behavior Analysis at Scale
Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in lon...
HuggingFace
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origam...
HuggingFace
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
Multimodal models often build on architectures designed for generative vision-language modeling, typically combining ...
HuggingFace
Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
Spatial return models take the interaction matrix as given and leave feedback uninterpreted. We construct a bandwidth...
HuggingFace
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Portfolio risk assessment ordinarily relies on reliable estimates of cross-asset return covariances, which are diffic...
HuggingFace
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of...
HuggingFace
Small Language Models as Judges for Rubric-Based Reinforcement Learning
Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring res...
HuggingFace
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Agent performance depends jointly on the model parameters and the executable harness code that manages context and co...
HuggingFace
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
A language model's prediction of its next token develops across layers, and lens methods track this process by decodi...
HuggingFace
An Empirical Study on Zero-Data Bootstrapping for Conversational Recommender Systems
Conversational Recommender Systems (CRS) typically require domain-specific dialogue data, which is costly, scarce, an...
HuggingFace
Cliff: Learning Process Rewards from the First Mistake
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LL...
HuggingFace
Kirin: Animal Motion Generation from In-the-Wild Video
Understanding animal motion is fundamental to modeling animal behavior and biomechanics, yet progress in this area la...
HuggingFace
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Competitive programming has become a key test of large language model reasoning, with international competitions such...
HuggingFace
On the Design Fundamentals of Pixel Text Representation Learning
Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet ex...
HuggingFace
Language Models Can Control Their Own Attention
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to fi...
HuggingFace
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single ...
HuggingFace
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model ...
HuggingFace
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral e...
HuggingFace
Aspire: Can Models Self-Evolve from Vague Goals?
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at re...
HuggingFace
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external ex...
HuggingFace
Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers
Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts m...
HuggingFace
CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing
The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe com...
HuggingFace
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language ...
HuggingFace
VibeVoice-ASR-Streaming Technical Report
Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-t...
HuggingFace
SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions
Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for information. Snap-and-...
HuggingFace
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize...
HuggingFace
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable ima...
HuggingFace
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering
Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involv...
HuggingFace
Exploring Collaboration between a language and a non-language agent
LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through ...
HuggingFace
Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents
Professional agent tasks often depend on conventions that are absent from public corpora, yet benchmarks rarely contr...
HuggingFace
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decom...
HuggingFace
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them through multi-step ...