Nonuniformity Principle in Human-AI Coworking
As generative AI is increasingly applied to automate multi-step and high-stake workflows, human judgment and involvement remain essential for ensuring the quality of AI-generated o...
Papers
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention r...
Recursive Harness Self-Improvement
Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This ...
Loop the Loopies!
We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters ...
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, a...
RecGPT-V3 Technical Report
Large language models (LLMs) are transforming recommender systems from matching co-occurrence patterns in historical behavior toward reasoning about the intent that drives it. RecG...
Understanding Reasoning from Pretraining to Post-Training
Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the p...
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-s...
Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausi...
SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction
Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneou...
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computa...
An Exam for Active Observers
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued ...
When Does Muon Help Agentic Reinforcement Learning?
Muon is competitive with AdamW in large-scale pre-training, but its value for reinforcement-learning (RL) post-training remains unclear. We study vanilla Muon in sparse-reward agen...
Interactive Training 2: Auditable Control Plane for Live Model Training
Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code. We present Interactive Training 2, an open-source contro...
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testin...
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether...
Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models
In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corr...
Trajectory-aware Cross-view Geo-localization with Sequential Observations
Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods show that sequential queries such as video clips yield richer spa...
WanSong v1.0 Technical Report
Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fidelity long-form audio while supportin...
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increa...
BadWAM: When World-Action Models Dream Right but Act Wrong
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generati...
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL...
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based rein...
RoboTTT: Context Scaling for Robot Policies
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training re...