World Models & Planning - Weekly Roundup

Directly learning robot action policies from raw video without explicit action labels unlocks scalable world action models.

Autoregressive video models can now perform explicit, goal-directed reasoning by jointly predicting the final outcome and intermediate steps, achieving state-of-the-art performance with 75% fewer training steps.

A single set of learned manipulation skills transfers to the real world with 78% success, bypassing the need for task-specific fine-tuning or re-training on real data.

Current omnimodal video embeddings struggle with physical reasoning, yet specific physics can be recovered and leveraged to significantly improve the physical fidelity of generated videos.

Robot skills can be dramatically improved post-training by autonomously generating practice tasks, diagnosing failures with privileged simulator states, and iteratively refining symbolic skills and system prompts, achieving near-perfect success on novel manipulation tasks.

Directly learning robot action policies from raw video without explicit action labels unlocks scalable world action models.

Autoregressive video models can now perform explicit, goal-directed reasoning by jointly predicting the final outcome and intermediate steps, achieving state-of-the-art performance with 75% fewer training steps.

A single set of learned manipulation skills transfers to the real world with 78% success, bypassing the need for task-specific fine-tuning or re-training on real data.

Current omnimodal video embeddings struggle with physical reasoning, yet specific physics can be recovered and leveraged to significantly improve the physical fidelity of generated videos.

Robot skills can be dramatically improved post-training by autonomously generating practice tasks, diagnosing failures with privileged simulator states, and iteratively refining symbolic skills and system prompts, achieving near-perfect success on novel manipulation tasks.

Persistent world models can now track objects even when they leave the agent's view, thanks to a novel actor-observer decoupling mechanism.

Achieve precise, intuitive 3D control over video generation by moving rigid object meshes, eliminating depth ambiguity and viewpoint inconsistencies.

Humanoid robots can learn entirely new complex manipulation skills at test-time by evolving reward programs, unlocking latent capabilities of pre-trained controllers.

Robust optimal policies and values for RMDPs are now computable in strongly polynomial time via a single LP, unifying and extending prior results across diverse uncertainty models.

Abstract future prediction in latent space significantly boosts LLMs' chemical reasoning and molecular outcome prediction capabilities.

Judgment models can solve complex problems when the answer is directly evaluable from the input, but fail catastrophically when simulation is required, even if they possess the underlying knowledge.

Discover the "why" behind ML benchmark gains with MECHVAR, a variance-guided approach that achieves near-optimal mechanism discrimination 100x faster than EIG.

Model-free Q-learning now guarantees optimal reachability policies in a broad class of MDPs, slashing sample complexity and memory needs.

Current egocentric video generation models fail to execute multi-step manipulation tasks realistically, often skipping crucial actions and exhibiting poor physical dynamics.

End-to-end learning of temporally predictable latent spaces for world models unlocks superior future scene understanding without the need for separate representation and prediction training stages.

A novel policy optimization method bypasses critic action gradients entirely, achieving faster, more robust updates and improved exploration in continuous control.

A robot can learn its partner's hidden physical limitations simply by watching it collaborate, enabling seamless coordination on novel tasks without explicit communication.

Intrinsic motivation can be learned from system dynamics alone, unlocking unsupervised discovery of essential robotic behaviors and complex locomotion.

Jointly training on simulation and experimental data unlocks balanced prediction in physical systems, outperforming sequential transfer and preserving crucial simulation-only knowledge.

Diffusion models can plan collision-free, multi-agent trajectories without any training data by leveraging analytical local scores derived from geometric constraints.

Ghost nodes and physics refiners unlock stable, accurate long-horizon hydrologic forecasts even with missing upstream boundary data.

Learned QKD attacks exploiting device drift can extract nearly 99% of the theoretical maximum information, shattering assumptions based on stationary channels.

Standard intrinsic rewards can fail to drive optimal exploration, even in simple settings, by neglecting the value of counterfactual information.

Robots can now plan complex, long-horizon tasks in novel environments by predicting sparse visual sub-goals, achieving 70% success in zero-shot real-world experiments.

An understanding-driven approach unlocks systematic spatial-memory management for world models, dramatically improving long-video generation quality.

Rejection-driven resubmission, not just population growth, is a primary driver of overwhelming reviewer burden in academic research.

Unified LLMs can now achieve state-of-the-art 3D generation and understanding by treating geometry as an explicit sequence of sparse octree tokens, without compromising core language abilities.

A single capable verifier can dramatically improve terminal agent action reliability, achieving higher success rates at lower costs than simply generating more trajectories.

Autonomous driving diffusion planners now learn to intrinsically adhere to driving rules and explain their decisions, significantly improving safety in challenging scenarios.

Learned world models can achieve real-time control in live games, outperforming behavioral cloning and maintaining high-frequency action loops.

Howard's policy iteration for deterministic MDPs is not strongly polynomial, exhibiting an exponential iteration complexity that separates it from the simplex method.

Sonar-only SLAM now achieves robust topological mapping by verifying loop closures with a sequence-aware approach, overcoming the inherent ambiguity of acoustic echoes.

Radar novel-view synthesis finally unlocks Doppler, achieving 90.7% object detection recovery by separating scene geometry from sensor spread and enabling zero-shot configuration transfer.

Agents can now reliably navigate evolving environments by maintaining a probabilistic 4D belief that accounts for hidden target movements and revises predictions based on intermittent, visibility-aware observations.

Robots can now learn from physical failures in real-time, autonomously revising their own capabilities to achieve unprecedented long-horizon manipulation success.

An optimal threshold policy for irrevocable matching in growing trees loses at most twice the total-variation error of the true growth law, even when forecasts are misspecified.

Humans can directly control complex embodied agents using a handful of learned, composable skills discovered through self-play, bypassing the need for low-level action control.

Imagined failures in a world model can pinpoint exactly which robot skill components need new demonstrations, boosting success from 13% to 75% with minimal data.

Language, when self-evolving and treated as a physical representation, can unlock state-of-the-art physical plausibility in video world models, even surpassing proprietary systems.

Separating policy roles in offline RL unlocks significant performance gains by tailoring updates for value bootstrapping versus direct action execution.

LLM agents trained solely in rule-generated fictional worlds achieve state-of-the-art transfer to real-world search tasks, outperforming agents trained on actual data.

Tree search on on-policy trajectories dramatically boosts policy gradient learning by uncovering rare high-return paths, outperforming PPO on Atari and MuJoCo with minimal bias increase.

Neural predictors can be made dynamically feasible without ground-truth controls by a frozen, post-hoc operator that enforces learned dynamics manifolds via iterative control correction.

Hybrid RL for bus holding suffers when simulators misrepresent passenger journey completion, leading to worse outcomes than purely offline methods.

State representation quality, not goal representation, is the critical bottleneck in offline navigation GCRL, with simple positional encodings boosting performance significantly.

Autonomous agents can recursively self-improve LLM-generated games, achieving superhuman performance and drastically cutting generation costs by internalizing development experience.

A single video tokenizer can achieve superior semantic alignment and fidelity compared to much larger models by directly conditioning on frozen visual features.

Streaming world models can now maintain consistent representations across minutes-long revisits without quadratic attention costs by leveraging a novel retrieval-based memory bank.

Reconstructing revisited scenes in streaming world models is now possible with constant memory, outperforming full-softmax attention by 30% on peak memory.

A single visual interface, action views, bridges the gap between video generation models and diverse robotic embodiments, enabling unified action modeling and execution.

Most current robotic manipulation policies fail to retain crucial historical information, leading to significant performance drops in partially observable tasks, but a novel memory framework boosts success rates across diverse challenges.

A 4B grounding foundation model achieves state-of-the-art visual grounding, outperforming larger models and boosting downstream robotic and autonomous driving performance by up to 24.8% in OOD settings.

Robots can adapt to unseen tasks purely through simulated imagination, boosting real-world manipulation success from 20% to 77% without requiring new human demonstrations or external environment rollouts.

Robot policies can now test and refine manipulation plans entirely within a learned visual simulator across ten distinct embodiments, gaining up to 21.4 percentage points in task success without any target-domain fine-tuning.

LLM agents abandon their own declared plans up to 78% of the time, but enforcing faithful execution via pattern-specific scaffolding nearly doubles benchmark success rates.

Robots no longer need human intervention to learn from their mistakes: foundation-model-guided exploration over modular skills can autonomously synthesize corrective rollouts that distill directly into low-level policy weights.

Multi-action weakly-coupled MDPs can shatter the theoretical $O(1/\sqrt{N})$ performance barrier to reach an $O(1/N)$ optimality gap simply by ditching heuristic priority ordering in favor of locally linear mean-field dynamics.

Multi-agent generative models can now provably satisfy complex, coupled hard constraints without centralized runtime coordination—even zero-shot scaling to agent counts never seen during training.

Causal generative models can now recover true joint distributions and counterfactual queries even when not a single complete record exists in the dataset.

Standard 5-second planning horizons miss over 90% of real-world passenger instructions, exposing a severe architectural failure mode in language-conditioned autonomous driving.

Predictive SSL can provably distinguish intrinsic process stochasticity from random observation noise—resolving a foundational puzzle behind why non-generative latent prediction captures genuine world dynamics.

Nonpreemptive queueing breaks standard myopic priority rules because optimal decisions fundamentally depend on the remaining horizon, yet certainty-equivalence Bellman planning can still match the theoretical lower bound at $\widetilde{O}(\sqrt{d/T})$ regret.

Closed-loop vision verification is no longer bottlenecked by intractable generative surrogates: compact stochastic world models cut parameter counts by 130× while resolving over 80% of previously unverified RGB state spaces.

Key contribution not extracted.

Video world models can now maintain persistent scene memory without ever-growing storage by warping and fusing low-rank features into a fixed-size HexMemory.

Co-evolved robot communication protocols fail to transfer robustly to the physical world, even with sensory calibration, revealing that ecological and navigational context is as crucial as the signaling process itself.

Decoupling structured semantics from frame-level actions and distilling autoregressive rollouts via shared, compressed memory tokens solves the long-standing trade-off between real-time responsiveness and multi-step drift in interactive world models.

Massive 100K-node routing problems can be solved in tens of seconds without learned heuristics simply by optimizing a compressed surrogate space to seed downstream solvers.

LLMs fail at chemical planning not from deficient reasoning capacity, but from an acute representation alignment bottleneck that disappears when structured through intermediate molecule and reaction abstractions.

Latent world models often fail at planning not because their dynamics predictions are inaccurate, but because distorted control geometry makes the latent optimization landscape hostile to sampling-based search.

Value-driven optimistic exploration has historically crumbled under deep network approximations, but diagnosing and repairing failure modes in uncertainty propagation allows pure model-free RL to beat complex model-based exploration baselines.

Model-based planning over dynamic spatial graphs cuts epidemic prediction error by 29% while guaranteeing the hard, per-period resource feasibility that standard RL controllers routinely violate.

Complex dynamical systems across diverse regimes share low-dimensional functional subspaces, allowing conditional mean operators for unseen distributions to be solved in closed form rather than learned from scratch.

Enforcing contractive dynamical structures onto learned latent disturbance representations delivers predictive disturbance accommodation without sacrificing the exponential stability guarantees essential for real-world adaptive control.

A single agent can disentangle true mechanisms from computational twin errors by jointly learning them, unlocking more accurate mechanistic discovery in complex biological systems.

A single diffusion operator can jointly predict intervention outcomes and select optimal measurements by treating decision quality as an interface property, outperforming Bayesian experimental design in cost-efficiency.

Predictive pretraining for parametric PDEs unlocks a 51.4% generalization improvement on unseen governing parameters by explicitly modeling latent dynamics geometry.