TacForcing is a streaming action-generation framework that integrates real-time tactile feedback during execution via a streaming action expert and execution-aware tactile attention, improving contact-rich manipulation.

EditaLive enables real-time human-centric live-stream video editing by adapting an image animation model to causal streaming generation with distilled two-step sampling and sparse attention.

PILOT enables live self-improvement by allowing a supervisor to steer active workers and distilling execution experience into reusable skills, improving accuracy and efficiency.

Game engines provide executable verification and long-horizon trajectories for reinforcement learning post-training of spatial world models, motivating a human-engine verification paradigm.

Procedura is a 3D modeling agent that generates editable, part-structured procedural assemblies with sharp geometry and validated articulation from text prompts.

An agentic framework combining LLMs and VLMs enables consistent, multi-instruction editing of long multi-shot videos while preserving spatiotemporal structure.

GameWAM is a unified world-action model for native video-game control that jointly predicts future visuals and executable keyboard-mouse actions using block-causal flow matching, mode-specific distributions, and block-cycle replanning.

Test-Time Policy Optimization enables label-free test-time training for mathematical reasoning by asymmetrically distilling agreeing rollouts and penalizing disagreeing ones, matching supervised performance.

Aphanta evaluates when image-editing intermediates improve multimodal reasoning by testing direct, editor-generated, and idealized visual states across tasks.

CaSKG calibrates procedural skill relations via counterfactual-causal graph construction to improve compact, executable retrieval for LLM agents.

Harness-Aware Training enables compact models to adapt to evolving digital-avatar harness configurations with low latency and high accuracy.

CaRGo-T improves multimodal humor understanding by modeling causal relationships as graph-based reasoning structures interpreted by vision-language models.

The study formalizes probabilistic alignment for world models, introduces PAWBench and PAWEval to evaluate video generators as stochastic samplers, and finds current models fail to match reference behavior distributions.

UrbanGround evaluates whether multimodal language model agents can sustain reliable navigation and spatial reasoning in a realistic 3D city replica, revealing that local perceptual skills fail to compose into extended goal-directed behavior.

Zero-WAM enables robotic manipulation of unseen tasks by conditioning a causal video-action model on in-context human video guidance, supported by an automatically generated dataset and a future-chunk prediction objective.

WikiSkill co-evolves reusable agent skills with a persistent knowledge base to systematically accumulate experience and improve performance across models.

Self-OPD eliminates task-specific teachers in flow matching by using self-explored stochastic branches and normalized advantages to optimize the velocity field for multi-objective alignment.

Evolution strategies improve reasoning diversity and Pass@K over GRPO through sparse functional updates and population diversity, supporting a hybrid training approach.

Magpie is a real-time generative rendering system that separates gameplay logic from visual generation to preserve interactive designability while reducing asset requirements for game prototypes.

Agentic data generation is framed as constrained distribution design over factorized experience tuples, emphasizing execution-grounded accuracy, learner-relative complexity, and diversity rather than scale alone.

A benchmark of contrastive GUI instructions reveals that vision-language models mostly fail to localize interface elements rather than misunderstand spatial relations, though marking candidates substantially improves selection.

Multilingual self-play reveals that large language models exhibit significant cross-lingual skill inconsistencies in reasoning and strategy, partly recoverable by altering intermediate reasoning language.