All entries

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

arXiv:2608.06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world s

Applications

Cybersecurity is the ultimate venue for real-world RL: 2p0s game, sim-able, clean reward signals Cybersecurity in a year will be fought betw…

DGX agent

Cybersecurity is the ultimate venue for real-world RL: 2p0s game, sim-able, clean reward signals Cybersecurity in a year will be fought between swarms of good and bad playing an exceptionally fast, co

applicationssonya-huang--x

10 Aug 2026

DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation

arXiv:2602.20860v2 Announce Type: replace Abstract: While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect n

safetyarxiv-cs-cv

Local Ai

DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding

arXiv:2608.06869v1 Announce Type: cross Abstract: We describe DAEP, team BIGC's submission to NLPCC 2026 Shared Task 1 Track 3: Difficulty-Aware Temporal Answer Grounding in Video Corpus (DA-TAGVC). T

local-aiarxiv-cs-cl

DATAREEL: Automated Data-Driven Video Story Generation with Animations

arXiv:2604.25220v2 Announce Type: replace Abstract: Data videos combine animated visualizations with synchronized narration to communicate quantitative information and are widely used in journalism, e

Agents

Deal Me Maybe: The Role of Emotions in Multi-Agent Negotiation

arXiv:2608.06922v1 Announce Type: new Abstract: Negotiation is a demanding social task for LLM agents, requiring strategic reasoning, persuasion, and interpersonal adaptation. Yet existing benchmarks

agentsarxiv-cs-ai

Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning

arXiv:2608.06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reas

Local Ai

Decentralized Indoor Localization Based on A Sparse Gaussian Process with Reduced-Dimensional Inputs for Real-Time Sensing and Training on IoT Devices

arXiv:2409.00078v2 Announce Type: replace-cross Abstract: As a large number of Internet of Things (IoT) devices are deployed in the field, there arises huge potential of edge computing for indoor loca

local-aiarxiv-cs-lg

Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models

arXiv:2608.06994v1 Announce Type: cross Abstract: World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion pla

tutorialsarxiv-cs-ai

Deep Evidential Regression for Sparse Forest Height Estimation from Multimodal Satellite Imagery

model-releasesarxiv-cs-cv

arXiv:2608.06406v1 Announce Type: new Abstract: Accurate estimation of forest height from satellite imagery is essential for applications such as carbon accounting, biodiversity monitoring, and ecosys

DeepSeek V4 Flash 0731 is the ‘killer app’ that is going to sell A LOT of DGX Sparks

model-releasesr-localllama

Having a ‘Killer Application’ that everyone wants to use helps sell hardware, plain and simple. DeepSeek V4 Flash 0731 isn’t an app of course, but I think it’s going to be the major catalyst for getti

Defining Energy Indicators for Impact Identification on Aerospace Composites: A Structured Feature Selection Approach Guided by Domain Knowledge

arXiv:2511.01592v2 Announce Type: replace Abstract: Energy estimation is critical to impact identification on aerospace composites, where low-velocity impacts can induce internal damage that is undete

tutorialsarxiv-cs-lg

Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal

arXiv:2608.06939v1 Announce Type: new Abstract: Adverse weather causes diverse and complex image degradations, severely compromising the reliability of computer vision systems. Existing all-in-one res

safetyarxiv-cs-cv

Density-aware Hierarchical Clustering Based on Element-Categorized Connection Subgraphs

arXiv:2608.06990v1 Announce Type: cross Abstract: Clustering is a fundamental data mining technique for pattern recognition through unsupervised learning. Among various clustering methods, hierarchica

Density-Functional Excited-State Gradients and Nonadiabatic Couplings on a Consumer GPU from a Contraction-DAG

arXiv:2608.06536v1 Announce Type: cross Abstract: Nonadiabatic dynamics needs an excited-state gradient and an interstate nonadiabatic coupling matrix element (NACME) at every nuclear geometry, and a

safetyarxiv-cs-lg

Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model

arXiv:2608.07361v1 Announce Type: cross Abstract: Vision-language-action (VLA) models route driving decisions through a deep language model, but it is unclear how much of that depth the action itself

researcharxiv-cs-cv

Agents

Detection and Ranging of Transient Extrinsic Contacts Based on 6D Dynamic Tactile Sensing

arXiv:2608.07075v1 Announce Type: new Abstract: Delicate manipulation often involves transient and subtle collisions between a grasped object and the environment. While the human hand localizes these

agentsarxiv-cs-ro

Deterministic Preprocessing and Interpretable Fuzzy Banding for Cost-per-Student Reporting from Extracted Records

arXiv:2603.04905v2 Announce Type: replace-cross Abstract: Administrative extracts are often exchanged as spreadsheets and may be read as reports in their own right during budgeting, workload review, a

DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training

arXiv:2608.07147v1 Announce Type: new Abstract: Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from co

safetyarxiv-cs-ai

Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

arXiv:2608.07430v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mech

Applications

Direct Visual Grounding by Directing Attention of Visual Tokens

arXiv:2511.12738v2 Announce Type: replace Abstract: Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive l

applicationsarxiv-cs-cv

Dirichlet Follow-the-Leader Closes the Gap in Simultaneous Multiclass U-Calibration

arXiv:2608.06656v1 Announce Type: new Abstract: Can one forecaster attain the optimal regret rate for every bounded proper loss and also adapt to every smooth proper loss? Recent work answered this up

researcharxiv-cs-lg

Discovering Conceptual Metaphors Across Topics and Media Types

arXiv:2608.06652v1 Announce Type: new Abstract: Conceptual metaphors guide our thinking and actions by allowing us to reason about more abstract experiences (e.g., paying taxes) in terms of more concr

tutorialsarxiv-cs-cl

Divergent Response Modes in Frontier Language Models Under Steering Pressure

arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behav

Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness

arXiv:2608.06613v1 Announce Type: cross Abstract: Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remai

safetyarxiv-cs-ai

Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events

arXiv:2608.06485v1 Announce Type: cross Abstract: Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the develop

Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation

model-releasesarxiv-cs-cl

arXiv:2608.06718v1 Announce Type: new Abstract: Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paraling

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

arXiv:2608.07067v1 Announce Type: new Abstract: Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static

Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?

arXiv:2608.07006v1 Announce Type: new Abstract: Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all av

researcharxiv-cs-cl

Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints

arXiv:2608.06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measura

safetyarxiv-cs-ai

Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance

arXiv:2608.06539v1 Announce Type: new Abstract: False-presupposition QA (FPQA) tests LLMs on their ability to identify false presuppositions in questions and abstain or correct them rather than reinfo

tutorialsarxiv-cs-cl

Industry

🔗 Download Muse Glimmer on @huggingface: https://huggingface.co/meta-models 🔗 Read the technical blog: https://go.meta.me/museglimmer 🔗 F…

🔗 Download Muse Glimmer on @huggingface: https://huggingface.co/meta-models 🔗 Read the technical blog: https://go.meta.me/museglimmer 🔗 Find resources: https://developer.meta.com/ai/models/muse-glimme

industryclem-delangue--x

DREAMS: Diverse Reactions of Engagement and Attention Mind States Dataset

arXiv:2608.06382v1 Announce Type: cross Abstract: Active attention and engagement are important in improving users' learning experiences. Engagement refers to the level of involvement and interest ind

researcharxiv-cs-cv

Local Ai

Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning

arXiv:2608.07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical evidence for multi-node training on desktop-class

local-aiarxiv-cs-lg

Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification

arXiv:2608.06943v1 Announce Type: new Abstract: Cross-modal Re-Identification (ReID) aims to retrieve the same identity across heterogeneous imaging modalities and has been widely studied in visible-i

safetyarxiv-cs-cv

Agents

Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection

arXiv:2608.06706v1 Announce Type: cross Abstract: Latent world models plan by predicting future states from an action, but when a scene contains motion the agent does not control, they quietly go acti

agentsarxiv-cs-ai

DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion

arXiv:2608.07401v1 Announce Type: cross Abstract: The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires jointly mo

researcharxiv-cs-lg

ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness

model-releasesarxiv-cs-cv

arXiv:2608.06841v1 Announce Type: new Abstract: Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and inte

EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation

model-releasesarxiv-cs-ro

arXiv:2511.18112v3 Announce Type: replace Abstract: Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. H

ED-CSP: Crystal Structure Prediction from Electron Diffraction

arXiv:2608.06448v1 Announce Type: cross Abstract: Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem.

Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning

model-releasesarxiv-cs-lg

arXiv:2608.07158v1 Announce Type: new Abstract: Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial tran

EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentation

arXiv:2608.07299v1 Announce Type: cross Abstract: Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertai

ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink

arXiv:2608.06942v1 Announce Type: cross Abstract: The acquisition of multispectral imagery via small satellites (e.g., CubeSats) presents significant data downlink challenges due to high data volumes

researcharxiv-cs-cv

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

arXiv:2608.07196v1 Announce Type: new Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system

Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics

arXiv:2604.00669v2 Announce Type: replace Abstract: This study examines the challenges of modeling complex and noisy data related to socioeconomic factors over time, with a focus on data from various

tutorialsarxiv-cs-lg

EntropyMoE: Entropy-Aware Sparse Expert Routing for Tokenizer-Free LLMs

arXiv:2608.06398v1 Announce Type: new Abstract: Recent byte-level large language models (LLMs) have made tokenizer-free modeling increasingly competitive by grouping bytes into dynamically sized patch

EpiFlow: A framework for improving the utility of wastewater signals for disease forecasting

arXiv:2608.06671v1 Announce Type: new Abstract: Wastewater-based surveillance is an effective tool for disease monitoring and can provide early warning of outbreaks. Although wastewater viral loads (W

researcharxiv-cs-lg

Applications

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

arXiv:2511.09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity. In particular, their act

applicationsarxiv-cs-lg