LeWAM: End-to-End World and Action Modeling with JEPAs
Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and ...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution
Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been ...
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, th...
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
When a coordinator compares answers from heterogeneous foundation models, self-reported confidence may have different meanings across responders and changing workloads. This paper ...
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-mo...
Foundations of Large Language Models
This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technolo...
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene i...
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents ...
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual grounding, external retrieval, and fact composition. A key cha...
Thinking Inertia: LLMs Keep Thinking When Told Not To
Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study LLMs' no-thinking beh...
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies either inject 3D ...
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference...
Reflex: Visually Grounded Reactive Humanoid Control
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passing cart, or pass a box tossed during truck unloading. These e...
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assign...
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intelligence demands predictive spa...
Recurrent Harness for Agentic Continual Learning
Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent har...
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies. Yet most existing approaches remain text-centric, linearizing spati...
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead...
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effective...
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datase...
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, th...
AI-Driven, Timing-Aware Power Optimization
Post-route power recovery changes cell choices under tightly coupled timing, electrical and physical constraints, and the value of each change depends on what it costs to repair it...
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view...
Pumpire: Unified Benchmark for Metric Distance Estimation
We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation models, with or without depth p...