Latest AI/ML research from ArXiv and Papers with Code
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention r...
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 ...
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 ...
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...
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...
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...
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...
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...
Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneou...
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...
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 ...
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...
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...
Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testin...
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...
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...
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...
Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fidelity long-form audio while supportin...
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...
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...
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL...
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...
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...
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persis...