Contrastive Action
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning
Announce Type: new Abstract: Embodied agents need to predict the future consequences of candidate actions in order to plan effectively before execution. Existing visual dynamics models learn by reconstructing future visual states or rolling out dense latent representations, which spreads learning capacity across visually salient but planning-irrelevant content rather than the action-conditioned changes that drive manipulation outcomes. We propose CAPE, a Contrastive Action-conditioned...
Contrastive Representation Regularization for Vision-Language-Action Models
Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for...
SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
arXiv:2602.09580v4 Announce Type: replace Abstract: Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative likelihood-based updates during fine-tuning because action probabilities are intractable. In contrast, conventional Gaussian policies collapse under multimodality, particularly when actions are executed in...
Cambodia’s ‘performative’ crackdowns fail to stop scam centres: Amnesty
Cambodia’s ‘performative’ crackdowns fail to stop scam centres: Amnesty The rights group said it identified 86 scam compounds operating across Cambodia as of April, up from 53 a year earlier That contrasts with official statements that authorities had taken action against more than 250 scam centres nationwide. The findings cast doubt on government assertions that the industry had been significantly weakened. Senior Minister Chhay Sinarith said in February that online scam activity had been...
World2Act: Latent Action Post-Training from World Model Dynamics
arXiv:2603.10422v2 Announce Type: replace Abstract: World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to...
Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
arXiv:2606.01865v1 Announce Type: new Abstract: Diffusion policies have recently emerged as a powerful framework for robotic manipulation. However, like other behavior cloning methods, they remain vulnerable to distributional shift, often requiring human-in-the-loop interventions to correct failures during deployment. These interactions naturally provide paired supervision in the form of the robot's undesired actions and the human teacher's corrective actions.
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
arXiv:2606.03868v1 Announce Type: new Abstract: Recent world action models leverage video foundation models by aligning broad visual-dynamics priors with executable robot actions. We revisit this alignment from a distributional perspective.
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
arXiv:2605.26371v2 Announce Type: replace Abstract: Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and reusing temporally-extended skills. However, obtaining skills that are actually reusable remains an open challenge. Towards this end, we focus on abstractions that exploit the intuition of local dynamics: local transitions in different global contexts require...
Reinforcement Learning from Rich Feedback with Distributional DAgger
Announce Type: new Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional variant of the classic...
Reinforcement Learning from Rich Feedback with Distributional DAgger
arXiv:2606.05152v2 Announce Type: replace Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional...