Hugging Face Daily Papers
500 articles archived · Visit source ↗ · RSS
-
Hugging Face Daily Papers research 9d ago
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
Abstract Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture…
10 -
Decoding Children's Gait Behavior
Abstract We introduce a new problem domain for human action recognition: the fine-grained analysis of children's gait behaviors from standard RGB video. We specifically target the ambulatory patterns of children aged 3-17 years. Such behaviors arise naturally in the diagnosis…
37 -
MiniWorld: Democratizing the Training of Video World Models from Scratch
Abstract Video world models predict future observations conditioned on historical observations and control signals, enabling long-horizon generation through autoregressive state transitions. Unlike conventional video generation models that primarily capture visual appearance and…
18 -
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Abstract Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for studying this capability because they retain preferences, task histories, tool routines, and learned skills across…
6 -
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
Abstract Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge…
8 -
PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs
Abstract Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems hide request-level failures by scoring only completed outputs; direct image generation is not element-editable, while coding-agent workflows are costly.…
35 -
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
Abstract Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood. We systematically characterize how optimization hyperparameters, compute allocation,…
18 -
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Abstract Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges…
29 -
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
Abstract We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration. Preliminary evaluations reveal two critical bottlenecks in…
8 -
Push-Wiper: Toward General-Purpose Robotic Cleaning across Varied Stains and Surfaces with Segmented Pushing Trajectories
Abstract Viscous stains, characterized by high viscosity and complex rheological properties, remain a major challenge for robotic surface cleaning. Conventional wiping often spreads the stain, while scrubbing provides stronger friction but risks damaging the surface. In this…
12 -
ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts
Abstract World Action Models (WAMs) have emerged as a promising paradigm by jointly modeling robot actions and future visual dynamics. However, their reliance on pixel-generative future supervision can entangle action-relevant state transitions with task-irrelevant visual…
5 -
Quo Vadis, World Modeling?
Abstract Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query…
19 -
ExplainBench: Evaluating Code Explanations from Agents
Abstract Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes, spanning tens to hundreds of lines. This makes manual review of agent results increasingly…
30 -
Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation
Abstract Industrial recommenders increasingly adopt the pretrain-then-transfer paradigm, yet behavioral distribution drift raises two questions: what to learn from behavior sequences, and how to transfer the learned knowledge while the pretrained model is continually refreshed.…
29 -
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Abstract Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time,…
32 -
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
Abstract Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation…
24 -
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Abstract Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling remains constrained by scarce multimodal data, particularly the lack of large-scale and…
8 -
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
Abstract Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio token sequences incurs substantial computational overhead, demanding aggressive token…
6 -
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
Abstract Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly on discrete tokens. Existing continuous language models either inherit embedding spaces…
32 -
CAPEval: A Decoupled Caption Evaluation across Understanding and Generation
Abstract Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. However, previous evaluations treat the caption quality as a single scalar objective, which conflates two distinct properties: (1) how much visual information…
22 -
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Abstract Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained credit assignment in long-horizon TIR scenarios.…
26 -
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Abstract Self-evolving agents increasingly convert interaction histories into reusable skills that persist beyond individual tasks. While prior work studies memory and retrieval poisoning, such attacks only affect agents when poisoned records are retrieved as context. We uncover…
28 -
UniWorld-Design: From Pixel Generation to Layer-Native Design
Abstract We introduce UniWorld-Design, a framework that redefines image generation from flat pixel synthesis to structured visual composition, with semantic RGBA layers as the atomic units of generation, understanding, and editing. Our key insight is that pixels define how an…
17 -
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
Abstract A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use…
25 -
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Abstract On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this…
28 -
Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge
Abstract Enterprise question answering requires models to acquire proprietary knowledge without discarding general capabilities. We present Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data…
24 -
To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
Abstract Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one concrete source: deletion avoidance, the systematic tendency to retain code that an intended…
8 -
SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
Abstract World Action Models (WAMs) couple action generation with prediction of future states. Their effectiveness depends on whether future dynamics are modeled in a space that is both aligned with action generation and sufficiently geometry-aware to capture where and how…
23 -
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Abstract LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can…
21 -
Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI
Abstract Multimodal clinical models are usually judged on accuracy with every modality present, but deployment removes modalities; an echocardiogram is often unavailable where an ECG is routine. Two questions then matter beyond the size of the accuracy loss: which modality was…
14 -
Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
Abstract Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge. We…
26 -
Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV
Abstract Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and episodic-memory schemes therefore rest on a premise rarely tested directly, that a retained event is still informative…
14 -
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
Abstract Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across…
13 -
ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures
Abstract Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meaningful knowledge, often not presented in the text of a research publication. The Sci-ImageMiner benchmark dataset,…
6 -
GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation
Abstract Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data. Concerning flood…
19 -
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
Abstract Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging because a single model must capture both global structure and local texture in the same high-dimensional space. While recent work improves pixel diffusion…
7 -
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
Abstract Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates a repair-assignment problem: the same visible failure may call for model post-training,…
38 -
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
Abstract Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes. While LLM-based agents can automate this trial-and-error process, allowing the LLM to both select modification…
37 -
DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents
Abstract Accurate prediction of object trajectories during manipulation is essential for closing the perception-action loop. Progress is limited on two fronts: available datasets lack fine-grained language-to-motion annotations, and existing predictors either rely on privileged…
19 -
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Abstract Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Existing methods, however, typically connect these states to the reasoning trajectory through…
8 -
GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding
Abstract Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric. They process the entries in a fixed order, one at a time, propagating each rounding error to the entries not yet processed…
5 -
DiffusionGemma Technical Report
Abstract We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the…
13 -
Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts
Abstract Vision-language MoE batches contain different numbers of image and text tokens. Image resolution, image count, tiling, and prompt length all change this token mix. We call the standard token-level Switch auxiliary loss Std-Aux. Std-Aux balances only the mixed load, so…
33 -
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Abstract Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to address knowledge-intensive and dynamically evolving open-world problems. To move beyond this limitation, multimodal…
24 -
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
Abstract Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene,…
13 -
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
Abstract Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes ill-defined when reference and target objects differ substantially in morphology,…
23 -
DAPD: Dual-Anchored Policy Distillation
Abstract On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a privilege illusion: the student learns privilege-dependent behavior it cannot reproduce from its…
11 -
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Abstract Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within…
37 -
CADENA: Stepwise CAD Reverse Engineering
Abstract Computer-Aided Design (CAD) underpins modern engineering, yet converting existing shapes into editable models still demands substantial expert effort. Most AI systems emit the entire CAD program in a single pass, never inspecting the intermediate geometry. In contrast,…
37 -
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation
Abstract Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-off: inefficient multi-step diffusion prohibits streaming generation, whereas real-time autoregressive approaches suffer from error accumulation and identity drift. To…
24