Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2608. 09298v1 Announce Type: cross Abstract: Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation.
arXiv:2608. 08618v1 Announce Type: cross Abstract: Industrial device commissioning requires engineers to manually extract hundreds of protocol-specific parameters from heterogeneous PDF manuals and transcribe them into supervisory control systems, a time-intensive, error-prone workflow.
arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.
arXiv:2608. 07542v1 Announce Type: new Abstract: Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of whichever metric they optimise rather than testing the hypotheses that motivate the experiments.
arXiv:2608. 08814v1 Announce Type: cross Abstract: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos.
arXiv:2608. 09898v1 Announce Type: cross Abstract: Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts.
arXiv:2604. 01476v2 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task.
arXiv:2608. 08947v1 Announce Type: cross Abstract: Current hazard detection systems in autonomous driving may develop mesa objectives, learned internal goals that achieve high training performance through spurious correlations rather than genuine hazard recognition.
Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts. Verifier-free test-time scaling (or VF-TTS) is gaining extensive attention as a mechanism to enhance Large Language Model (LLM) reasoning, primarily because we do not have access to such high-quality verifiers in many real-world applications.
Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains challenging due to temporal ghosting, geometry drift, and inconsistent object motion. Recent latent video diffusion models have achieved impressive visual quality, but directly applying them to structured traffic scenes often leads to unstable geometry and degraded temporal coherence over extended horizons.
Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this promise requires precise action-conditioned transitions rather than merely plausible outputs.
While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds. Imitation learning policies are inherently limited by hardware constraints and the speed of the operator during data collection.
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv:2608. 07065v1 Announce Type: cross Abstract: Action-chunking visuomotor policies learn from demonstrations and improve temporal consistency by predicting short action sequences rather than single-step commands.
arXiv:2608. 06587v1 Announce Type: cross Abstract: Robot swarms utilize many independent limited-sensing agents to produce complex emergent behaviors without requiring centralized control.
arXiv:2608. 06469v1 Announce Type: cross Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation.
arXiv:2608. 01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.
arXiv:2509. 06296v2 Announce Type: replace-cross Abstract: Traditional on-policy reinforcement learning (RL) controllers for quadrupedal locomotion often suffer from low data efficiency, requiring millions of interactions with simulated environments to achieve stable control.
arXiv:2608. 06917v1 Announce Type: new Abstract: Recent Large Multimodal Models (LMMs) have achieved impressive performance in recipe generation from food images.
arXiv:2608. 07018v1 Announce Type: cross Abstract: Horizon detection in images of ice-covered waters is a challenging problem for maritime navigation due to low contrast between water and sky, cluttered ice structures, and varying illumination conditions.