Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.34610v1 Announce Type: new Abstract: Vision-language anomaly detectors describe normal and abnormal appearance with text, and their gains are commonly credited to the semantic content of t...
arXiv:2610.34734v1 Announce Type: new Abstract: Frequency-domain information is beneficial for semantic segmentation. However, existing frequency-based methods often suffer from insufficient frequenc...
arXiv:2610.35132v1 Announce Type: new Abstract: Positron Emission Tomography (PET) provides important metabolic information for tumor detection and staging but remains significantly less accessible t...
arXiv:2610.35312v1 Announce Type: new Abstract: Monocular occupancy prediction in indoor scenes aims to recover a scene's 3D geometry and semantics from a single RGB image. Existing methods are restr...
arXiv:2610.35450v1 Announce Type: new Abstract: Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, since aerial objects appear at arbitra...
arXiv:2610.35806v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models such as VGGT regress cameras and geometry in a single forward pass, but they report no uncertainty for the camera...
arXiv:2610.34085v1 Announce Type: cross Abstract: Safe indoor operation requires autonomous tracking of objects that are not directly visible to the robot. Optical non-line-of-sight (NLoS) methods de...
arXiv:2610.35642v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-o...
arXiv:2602.06663v3 Announce Type: replace Abstract: Unified multimodal models (UMMs) have shown impressive capabilities in complex natural image generation. However, their potential in computer-use p...
arXiv:2603.28064v2 Announce Type: replace Abstract: This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geo...
arXiv:2605.13803v2 Announce Type: replace Abstract: Video temporal grounding (VTG) takes an untrimmed video and a natural-language query as input and localizes the temporal moment that best matches t...
The paper introduces Interaction-Effect Propagation (IE-Prop), a model that estimates error risk in large language model (LLM) based multi‑agent systems by conditioning on whether upstream agents are correct or incorrect. IE‑Prop learns separate effects for each sender‑receiver interaction, combines them using the sender’s estimated error risk, and recursively propagates these risks through the execution graph. Experiments on three architectures and benchmarks show that IE‑Prop improves final‑node AUROC by about 0.05 points over baselines and that multi‑step risk tracking adds an additional 0.03 AUROC in sequential systems.
The paper presents a child-centered harm taxonomy for AI systems and analyzes 1,331 publicly reported child-related AI incidents. It finds that harms are concentrated in representational, dignity-related, and psychological categories, often linked to deployment-context, governance, and misuse failures rather than model defects. The study highlights that model-level evaluations alone cannot anticipate the harm pathways most frequently documented for children, and recommends broader mitigations such as age assurance, consent verification, safety-by-design UX constraints, incident disclosure norms, and targeted auditing regimes.
The paper discusses how instruction hierarchy (IH) can be improved by training large language models on simulated instruction conflicts, particularly a newly identified type called goal‑goal conflicts. By fine‑tuning Qwen3.5‑9B and Gemma4‑12B‑it on examples of these conflicts, the authors demonstrate significant gains in IH performance across a variety of real‑world tasks, while maintaining negligible impact on non‑conflict tasks. The study suggests that incorporating goal‑goal conflicts into IH training sets can enhance model adherence to higher‑priority instructions.
MOSHO is a native discrete shark-inspired metaheuristic designed for hardware-aware neural architecture search, replacing continuous motion equations with discrete architecture-editing operators. It incorporates adaptive operator scheduling, energy-regulated restarts, and deferred crowding-distance truncation to improve exploration and search efficiency. On the NAS-Bench-201/HW-NAS-Bench benchmark, MOSHO achieves competitive Pareto fronts with a median normalized hypervolume of 0.9987 and IGD+ of 0.0064, while cutting search runtime by 96.4% (0.64 s vs. 17.72 s).
The paper investigates whether constrained decoding harms or helps large language model (LLM) performance. It introduces a taxonomy of three constraint types—format, validity, and reasoning—and shows that suitable constraints can preserve or even improve performance by eliminating invalid paths. Experiments across multiple model families reveal that perceived performance drops are mainly due to non-equivalent prompting and output formats, while validity constraints boost reliability and reasoning constraints can enhance accuracy when they guide beneficial reasoning trajectories.
AOS-Bench evaluates large language model agents as dynamic workload managers, testing their ability to handle multiple concurrent tasks under shared CPU and memory limits. The benchmark shows that isolated task success does not predict performance in a streaming workload, with significant drops in heavy and medium scenarios. Execution‑policy experiments reveal that simple concurrency controls can rival more complex management strategies, highlighting the importance of workload management as a distinct agent capability.
The paper introduces Iris, a framework that extends typed decision‑making models to multimodal settings where candidates can be images, text, or hybrids. Iris preserves key properties such as candidate‑order invariance, scalability, and cache reuse, and achieves high accuracy on a visual‑candidate benchmark while reducing latency through efficient encoding strategies. The authors also demonstrate significant speedups on GPU systems and outperform larger baseline models on MetaEncoder benchmarks.
arXiv:2610.34365v1 Announce Type: cross Abstract: Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows. This modularity crea...
arXiv:2610.34717v1 Announce Type: cross Abstract: Vision--language--action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. H...