2026-07-29

6 papers from arXiv

← Back to history

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Haolei Xu, Xiaowen Xu, Haiwen Hong, Zixuan Ni, Hongxing Li et al.

On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, w...

cs.CLcs.AIPR

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Simple AI, :, Yuteng Wei, Jinming Ma, Jiawei Wang et al.

Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale; robot-free UMI capture scales readily, and current practice uses the resulting data mainly for pre-training, adding a small real-robot "anchor" at post-training. We ask whether raising the fidelity of robot-free UMI dat...

cs.ROcs.CVcs.LGPR

Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosis

Adarsh Bhandary Panambur, Siming Bayer, Andreas Maier

Enhancing classification performance in mammography remains a persistent challenge across both small curated datasets and large-scale clinical cohorts. Conventional transfer learning approaches often neglect dataset-specific characteristics, while recent neighborhood-informed methods have been restricted to narrow tasks with rigid formulations, limiting their scalability to population-level datase...

cs.LGPR

Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics

Ya-Chia Shen, Woei-Leong Chan

Unmanned aerial vehicles (UAVs), particularly quadcopters, present unique challenges for autonomous control due to their underactuated dynamics: only four available control inputs must govern six degrees of freedom. This paper investigates a physics-aware, end-to-end deep reinforcement learning (DRL) approach that acts directly on low-level body inputs, total thrust and body torques $(T, τ_x, τ_y,...

cs.ROcs.LGeess.SYPR

LaP-Forensics: Latent-Pixel Consistency Guided Multimodal Reasoning for Deepfake Detection

Can Wang, Yuhao Wang, Yushe Cao, Canran Xiao, Fei Shen

Recent generative models can produce images with few obvious visual artifacts, weakening detectors and explanations that rely only on surface appearance. We present LaP-Forensics, a multimodal framework that augments RGB semantics with reconstruction-based forensic evidence. A frozen Stable Diffusion DDIM inversion-reconstruction model provides a fixed reconstruction reference, and its residual ma...

cs.CVACM MM

The LAIA Dataset: Labelled Attention for Intelligent Automobiles

A. Contreras, D. Porres, R. Abad, P. Cano, G. Villalonga et al.

The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of sensor data with ground-truth annotations. While modular architectures are widely used, end-to-end driving paradigms offer a promising alternative by directly mapping sensor inputs to control actions. However, their adoption is limited by challenges i...

cs.CVcs.AIcs.SEPR