arXiv:2604.00464v1 Announce Type: cross
Abstract: AI-driven conversational coaching is increasingly used to support workplace negotiation, yet prior work assumes uniform effectiveness across users. We challenge this assumption by examining how individ…
arXiv:2604.01044v1 Announce Type: new
Abstract: We introduce CROWD (City Road Observations With Dashcams), a manually curated dataset of ordinary, minute scale, temporally contiguous, unedited, front facing urban dashcam segments screened and segmente…
arXiv:2505.21505v3 Announce Type: replace
Abstract: Multilingual Alignment is an effective and representative paradigm to enhance LLMs’ multilingual capabilities, which transfers the capabilities from the high-resource languages to the low-resource la…
arXiv:2602.19053v2 Announce Type: replace
Abstract: Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusi…
arXiv:2505.19574v3 Announce Type: replace-cross
Abstract: Autonomous robots operating in complex, unstructured environments face significant challenges due to latent, unobserved factors that obscure their understanding of both their internal state and…
arXiv:2604.01043v1 Announce Type: new
Abstract: Recent advances in Video Foundation Models (VFMs) have revolutionized human-centric video synthesis, yet fine-grained and independent editing of subjects and scenes remains a critical challenge. Recent a…
arXiv:2604.00443v1 Announce Type: new
Abstract: If the same neuron activates for both “lender” and “riverside,” standard metrics attribute the overlap to superposition–the neuron must be compressing two unrelated concepts. This work explores how much…
arXiv:2604.01038v1 Announce Type: new
Abstract: Automated medical image segmentation has achieved remarkable progress with fully labeled data. However, site-specific clinical priorities and the high cost of manual annotation often yield scans with onl…
arXiv:2505.15808v2 Announce Type: replace-cross
Abstract: We present a neural framework for learning conditional optimal transport (OT) maps between probability distributions. Our approach introduces a conditioning mechanism capable of processing both…
arXiv:2602.01273v3 Announce Type: replace
Abstract: Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their heavy inference burden hinders real-world deployment….