Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2606.30943v2 Announce Type: replace Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between the...
arXiv:2609.13251v1 Announce Type: new Abstract: Commercial and advertising images are frequently affected by poor framing, partially cropped subjects, truncated text or logos, and insufficient contex...
arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...
arXiv:2606.29997v2 Announce Type: replace Abstract: Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limi...
arXiv:2609.15795v1 Announce Type: new Abstract: Streaming geometric foundation models are emerging as a compelling alternative to SLAM systems. Yet this streaming nature introduces a fundamental issu...
arXiv:2609.15392v1 Announce Type: cross Abstract: Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such sta...
arXiv:2512.20257v2 Announce Type: replace Abstract: With the rise of easily accessible generative tools for creating and manipulating multimedia content, the threat of realistic synthetic alterations...
arXiv:2605.16742v3 Announce Type: replace Abstract: Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geome...
arXiv:2606.00751v2 Announce Type: replace Abstract: Visual Speech Recognition (VSR) aims to recognize speech from visual cues such as lip movements. Still, its performance is fundamentally limited by...
PhysBrain 1.5 is a unified vision‑language model that learns to understand physical environments, generate actions, and predict future states by encoding language, end‑effector motion, and dense visual targets as discrete sequences and training them with autoregressive next‑token prediction. The model is pre‑trained on human interaction videos and fine‑tuned on human demonstrations, robot trajectories, and simulated experience, achieving an average score of 72.5 across 28 embodied understanding benchmarks and outperforming other open‑source models on 14 of them. It also demonstrates the ability to produce end‑effector trajectories and predict future scenes with spatially aligned RGB, depth, and robot‑mask outputs.
The paper introduces Verifier-Gated Multi-Expert On-Policy Distillation (VG‑OPD), a method that assigns teacher supervision at the token level based on each expert’s counterfactual gain on a specific answer criterion. VG‑OPD localizes supervision where experts disagree most with the student and weights it by criterion importance, integrating this into a gated KL advantage for reinforcement learning. Applied to scientific reasoning, VG‑OPD achieves top performance on seven benchmarks for 4B and 8B models, outperforming prior multi‑teacher distillation approaches.
arXiv:2606.02737v2 Announce Type: replace-cross Abstract: Dense retrieval compresses a passage into a single vector, but this compression is positionally skewed: early content dominates the embedding...
arXiv:2609.15855v1 Announce Type: cross Abstract: % !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk con...
arXiv:2602.07273v2 Announce Type: replace Abstract: Immersive applications such as virtual and augmented reality impose stringent requirements on frame rate, latency, and synchronization between phys...
arXiv:2608.16344v3 Announce Type: replace Abstract: Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and...
arXiv:2606.19100v4 Announce Type: replace Abstract: Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open...
arXiv:2609.14906v1 Announce Type: cross Abstract: The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system...
arXiv:2609.14377v1 Announce Type: new Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background...
arXiv:2609.14122v1 Announce Type: new Abstract: We study the challenge of sign language video mimicking: given a driving video and a single reference frame, synthesize a video where the target signer...
arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a laten...