All entries

Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language Models

arXiv:2608.08791v1 Announce Type: new Abstract: Diffusion language models use broad context to create text, suggesting they might handle input noise better than standard models. Testing reveals this i

researcharxiv-cs-cl

Unveiling the Secret of AdaLN-Zero in Diffusion Transformer

DGX agent

arXiv:2608.09438v1 Announce Type: new Abstract: Diffusion transformer (DiT), a rapidly emerging architecture for image generation, has gained much attention. However, despite ongoing efforts to improv

researcharxiv-cs-cv

11 Aug 2026

UPolarSQ: Polar Representation Learning for Optic Disc and Peripapillary Atrophy Segmentation and Quantification in Fundus Photographs

arXiv:2608.08771v1 Announce Type: new Abstract: Myopia-induced posterior-pole remodeling is frequently accompanied by Optic Disc (OD) deformation and Peripapillary Atrophy (PPA), both of which provide

Industry

Using the different models in different industries - your experience?

Hi all, I'm seeing so many conversations from people discussing how they're 'using the models wrong' and 'don't use Sol max as high is enough for you', yet all the conversations lack the nuance of wha

industryr-chatgpt

Applications

V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control

arXiv:2608.07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collect

applicationsarxiv-cs-lg

v0.32.8

model-releasesollama-releases

Muse Glimmer Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such

v0.32.9

model-releasesollama-releases

NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f

VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models

arXiv:2608.08622v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have demonstrated strong performance in open-ended video understanding, yet they remain prone to fluent responses u

safetyarxiv-cs-cv

VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction

arXiv:2608.09448v1 Announce Type: cross Abstract: Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains d

safetyarxiv-cs-cv

Variance reduction in lattice QCD observables via normalizing flows

arXiv:2603.02984v2 Announce Type: replace-cross Abstract: Normalizing flows can be used to construct unbiased, reduced-variance estimators for lattice field theory observables that are defined by a de

researcharxiv-cs-lg

VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

arXiv:2511.18121v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visu

Agents

VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge

arXiv:2608.07994v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documen

agentsarxiv-cs-ai

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

model-releasesarxiv-cs-cl

arXiv:2608.08477v1 Announce Type: new Abstract: We present VectraYX-Vision-1B, a sub-2B vision-language model (VLM) for Spanish/LATAM cybersecurity imagery, coupling a frozen SigLIP-so400m encoder to

VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting

arXiv:2608.09286v1 Announce Type: cross Abstract: Global medium-range weather forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields. Existing

Hardware

verdi: retrieval is not transfer for continual world model optimization

arXiv:2608.09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model t

hardwarearxiv-cs-ai

Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design

arXiv:2608.07978v1 Announce Type: cross Abstract: Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving

Verifiably grounded machine interpretation of lunar geology

arXiv:2608.09276v1 Announce Type: new Abstract: Planetary geology relies on historical, interpretive reasoning to reconstruct past events from diverse observations. Here, we present a step toward an a

local-aiarxiv-cs-cl

VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding

arXiv:2608.09698v1 Announce Type: cross Abstract: Great fiction earns its verisimilitude through precise details, from how a longsword is gripped to pierce armor gaps to why a bleeding corpse cannot y

researcharxiv-cs-cl

Vid2WAM: Distilling Video Diffusion Priors into World Action Models

arXiv:2608.08558v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling future visual dynamics and actions. However, their scalability and generali

safetyarxiv-cs-ro

VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation

model-releasesarxiv-cs-cv

arXiv:2608.09573v1 Announce Type: new Abstract: Natural-language-driven 'vibe coding' enables the one-shot generation of visually rich and interactive web applications, yet reliable assessment of thei

Applications

View-Adaptive Renderer for View-Consistent 2D-to-3D Generation

arXiv:2608.09110v1 Announce Type: new Abstract: Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipel

applicationsarxiv-cs-cv

VIGIL: Tackling Hallucination Detection in Image Recontextualization

model-releasesarxiv-cs-cv

arXiv:2602.14633v2 Announce Type: replace Abstract: We introduce VIGIL (Visual Inconsistency & Generative In-context Lucidity), a benchmark dataset and framework that provides a fine-grained categoriz

Vision-Language Grounding as Bidirectional Concept Correspondence

arXiv:2608.07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization proble

local-aiarxiv-cs-ai

Vision Meets WiFi: Physics-Grounded Estimation of Volumetric Mechanical Properties

arXiv:2608.07726v1 Announce Type: new Abstract: Estimating volumetric mechanical properties, including Young's modulus, Poisson's ratio, and density at each voxel, is intrinsically ambiguous from visi

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs

arXiv:2510.16598v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generat

Applications

Visual Distortion Detection in UGC Images Using Large Multimodal Models

arXiv:2608.09122v1 Announce Type: cross Abstract: The localized depiction of perceptual quality has long been a crucial, yet underexplored, challenge in image quality assessment (IQA). Existing approa

applicationsarxiv-cs-ai

Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding

arXiv:2608.08832v1 Announce Type: new Abstract: Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nod

local-aiarxiv-cs-cv

VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling

model-releasesarxiv-cs-cv

arXiv:2608.08630v1 Announce Type: new Abstract: Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-atte

VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression

arXiv:2608.08366v1 Announce Type: new Abstract: Spatial transcriptomics can resolve gene expression at single-cell resolution, but it is costly, limited to targeted panels of a few hundred to a few th

VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference

arXiv:2608.08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progres

safetyarxiv-cs-ai

VTO: Visual Tool Orchestration for Video Anomaly Detection

arXiv:2608.08219v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learn

WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models

arXiv:2608.08725v1 Announce Type: new Abstract: Vision-language-action (VLA) policies generate robot controls autoregressively, making closed-loop latency dominated by repeated target-model forward pa

researcharxiv-cs-ro

Walk-on-Spheres Monte Carlo and deep neural network approximations of elliptic PDEs with drift and killing

arXiv:2608.09494v1 Announce Type: cross Abstract: In this paper we provide Monte Carlo and deep neural network approximations for stochastic representations of solutions to linear elliptic partial dif

researcharxiv-cs-lg

Walking through Discussions: A Mobile Visual Analytics System for In-Situ Group Discussion Analysis

arXiv:2608.08617v1 Announce Type: new Abstract: Group discussion-based teaching is widely used to foster collaborative learning, yet teachers in physical classrooms often struggle to simultaneously mo

researcharxiv-cs-ai

Warp-free Cross-view Geo-localization via Feature-space Consensus Mining

arXiv:2608.09321v1 Announce Type: new Abstract: Cross-view geo-localization is challenging due to drastic viewpoint changes and large appearance discrepancies between street-level and satellite imager

local-aiarxiv-cs-cv

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

arXiv:2608.09447v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch o

safetyarxiv-cs-ai

Agents

We built the Agentic World Cup - LLMs that compete in 1v1 Soccer. [P]

Hey everyone - we've been building something particularly relevant to ML at large - The Agentic World Cup - a platform where Agents compete in sports. As you know, today's Agents can code, do math, an

agentsr-machinelearning

We quantized DeepSeek V4 0731 and benchmarked it against popular quants on 8× RTX 5090

model-releasesr-localllama

We converted the model from the original safetensors and found two issues. The first one made our quantization fail several times, the second one does not fail at all, it just quietly ruins the base 1

we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap!

model-releasesharrison-chase--x

we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap! We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Pri

Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems

model-releasesarxiv-cs-lg

arXiv:2401.04013v2 Announce Type: replace Abstract: Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of in

Weather- and Location-Aware Agentic Dining Recommendation: Leveraging LLM World Knowledge for Region-Sensitive Contextual Reasoning

arXiv:2608.07593v1 Announce Type: cross Abstract: Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Exi

local-aiarxiv-cs-ai

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks

arXiv:2506.01952v2 Announce Type: replace-cross Abstract: Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent

Hardware

What Irregularity Costs: CUDA C++, Rust, and Triton on a Hash-Blocked GPU Workload

arXiv:2608.08287v1 Announce Type: new Abstract: GPU language comparisons are almost always run on tiled dense linear algebra, where every toolchain is good and the differences are small. We implement

hardwarearxiv-cs-cv

What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files

arXiv:2608.08453v1 Announce Type: new Abstract: Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model (LLM) age

safetyarxiv-cs-ai

What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems

arXiv:2608.07565v1 Announce Type: cross Abstract: Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactio

What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions

model-releasesarxiv-cs-lg

arXiv:2608.08944v1 Announce Type: cross Abstract: A failed retrieval-augmented generation (RAG) answer can be consistent with several unseen responses to evidence repair. We introduce Pair-ID, an offl

When Can Fraud Operations Authorize Automation? A Decision-Support Framework for Fresh Audit Evidence and Review Workload

arXiv:2608.08577v1 Announce Type: new Abstract: Fraud operations must allocate events among automatic approval, analyst review, and automatic blocking even though the labels needed to evaluate these a

researcharxiv-cs-lg

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

arXiv:2608.09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks. However, their reliability u

researcharxiv-cs-ai