HuggingFace

The paper presents PARTS, a real-world subtask reinforcement learning framework that improves long-horizon manipulation tasks by focusing on bottleneck subtasks with minimal human intervention, achieving higher success rates in experiments.

This paper presents APort Vault, a benchmark for evaluating payment authorization in AI agents, featuring over 225,000 evaluations across 14 models to test security policies and the Open Agent Passport specification.

Gricea is an open-science platform for conversational AI research that enables configurable and deployable research artifacts to support replication, extension, and cumulative knowledge building.

This paper introduces OmniVChat, a task for native audio-visual dialogue, and presents a data engine, benchmark, and reinforcement learning method to train and evaluate omni models, demonstrating improvements on synthesized and human-recorded data.

MintAct is a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool use, achieving state-of-the-art performance on various benchmarks.

The paper introduces OmniVBench, a comprehensive benchmark for omni reference-to-video generation, and the Omni-R2VDataset, a large-scale training dataset, to evaluate and improve R2V models.

RecreationWorld introduces a scalable and verifiable framework for hybrid computer-use agents, providing environments across five platforms and a benchmark for evaluation.

GraphSkillEvo is an evolutionary optimization framework that represents agent skills as graph-structured artifacts to improve LLM performance, outperforming baselines on multiple benchmarks.

CodeMidas is an agentic pipeline that creates reinforcement learning environments from source code, scaling the training of coding agents and showing performance improvements on benchmarks like issue repair and program construction.

The paper proposes prediction-powered smoothing and validation methods for disaggregated AI evaluation, enhancing accuracy in point and interval estimates across domains with limited labeled data.

RefineEdit is a training-free prompt-to-prompt image editing method that uses a generative refinement network to enhance edit localization and background preservation, achieving top benchmark scores.

The paper evaluates compression schemes for Cellpose-SAM in stem cell microscopy, demonstrating that mixed-precision quantization achieves 6.76x reduction without catastrophic failures while maintaining segmentation accuracy.

Paint-Anything introduces a unified hex-prompt interface for color control in image generation and editing, trained on a custom dataset and evaluated on a new benchmark showing significant improvements in color fidelity.

This paper proposes a training-adaptive convolutional sparse coding framework that leverages information bottleneck principles for robust visual representation, achieving improved performance on CIFAR and ImageNet under input perturbations.

The paper presents TeleAntiFraud 2.0, an audio-based benchmark for evaluating telecom fraud detection models using a mixed-tree generation pipeline and frozen monthly sets to address evolving fraud scripts and near-domain negatives.

Introduces Movement Trend Guidance to enhance 3D diffusion policies in robotic manipulation by providing foresight without explicit trajectories, achieving improved performance on benchmarks like RoboTwin2.0 and LIBERO-40.

This paper studies the feedback loop where AI-generated reviews influence future training of AI reviewers, leading to reduced judgment diversity called 'scientific-judgment collapse,' and introduces TrustReviewer, an open-source system to mitigate this through curated training and activation steering.

DeformSmith is a framework for generating interactive, physically credible deformable assets for robot manipulation from text or images, using physics-guided hierarchical generation to improve quality and plausibility.

The paper introduces SELF-INDEX, a framework that enables search indexes to self-evolve autonomously, improving retrieval performance and benefiting downstream applications such as search agents and agent memory systems.

This paper investigates how on-policy distillation can cause length inflation due to EOS token mismatches between student and teacher models, and proposes a correction method by aggregating EOS probabilities to reduce response length.