APEX: Asynchronous Prefix Denoising for Extreme Compression
Fewer latent tokens promise cheaper diffusion. Yet aggressive latent compression creates a reconstruction-generation dilemma: adding channels improves reconstruction but makes gene...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Scaling Agentic Data for Long-Horizon Terminal Intelligence
Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not full...
Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating their capabilities through den...
MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement
Efficient visual tokenization requires balancing representation compactness with the preservation of fine-grained image content. Conventional grid-based tokenizers allocate tokens ...
InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architecture...
What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
Publishers and funders increasingly ask authors to disclose how AI tools contributed to a piece of research. In computational work the repository is where an author or an auditor w...
PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the base model's distribution. Its sampler, PowerMH, is slow becau...
Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrations conv...
Web$hell: A Unified Interface for Agentic Web Access
Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effective web access is becoming ...
SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models
Driving world action models (WAMs) learn from paired trajectories and future observations. Post-training with reinforcement learning allows the policy to explore alternative trajec...
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent und...
Learning Transferable World-Action Models from Task-Paired Human Videos
World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video next-frame prediction allows them to rely on appearance shared ...
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows. This deleg...
Harness^2: Recursive Agent Harnessing for an Open World
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatic...
Branching On-Policy Distillation
On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory realizes only one continuation at each decision, limiting super...
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environ...
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the spatial layouts from those vie...
Continually Post-training Small Models via Synthetic Self-distillation
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tunin...
Multi-Stream Attention Residuals
Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the s...
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrate...
Pristine Models
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures saf...
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical research question: Is on-polic...
GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GAT...
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit bet...