All entries

Diffuse the object, keep its label: curating detector training data from a few unlabeled photographs via VLM-built 3D vegetation scenes

model-releasesarxiv-cs-cv

arXiv:2608.09691v1 Announce Type: new Abstract: Labeled images of small objects hidden in vegetation are scarce, and detectors trained on them generalize poorly across sites. Rather than reusing label

Local Ai

Diffusion Image Editing via Asynchronous Token Decoding

DGX agent

arXiv:2608.09322v1 Announce Type: new Abstract: Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, naive

local-aiarxiv-cs-cv

11 Aug 2026

Diminishing Returns of Intelligence: The Non-Linear Relationship Between LLM Scale and User Perception in Short-Duration Open-Ended Social Human-Robot Interactions

model-releasesarxiv-cs-ro

arXiv:2608.08320v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to drive embodied social agents, yet it remains unclear whether larger models improve user perception

DINO-3DRA: Leveraging 2D Foundation Model Semantics for 3D Cerebral Aneurysm Segmentation

arXiv:2608.07767v1 Announce Type: new Abstract: Accurate aneurysm segmentation in 3D rotational angiography (3DRA) is hindered by extreme class imbalance, morphological similarity to vessels, and abse

Directed Neuro-Symbolic Stochastic Execution for Verification of Distributed Parallel AI Programs

arXiv:2608.07947v1 Announce Type: new Abstract: Distributed parallel Artificial Intelligence (AI) programs expose reliability gaps that conventional testing cannot close: parallel executions are non-d

Directional-Clamp PPO

model-releasesarxiv-cs-lg

arXiv:2511.02577v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is widely regarded as one of the most successful deep reinforcement learning algorithms, known for its robustness

DiSCo: Diffusion Sequence Copilots for Shared Autonomy

arXiv:2603.22787v2 Announce Type: replace-cross Abstract: Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requir

safetyarxiv-cs-ro

Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models

arXiv:2601.03115v2 Announce Type: replace Abstract: Emotion is a central dimension of spoken communication, yet, we still lack a mechanistic account of how modern large audio-language models (LALMs) e

safetyarxiv-cs-cl

Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity Optimization

arXiv:2608.08523v1 Announce Type: new Abstract: Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction hist

Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing

model-releasesarxiv-cs-cv

arXiv:2608.09752v1 Announce Type: new Abstract: Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation t

Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation

arXiv:2608.09826v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which acc

DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference

arXiv:2608.08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequen

Distilling CT Foundation Models into Editable Concept Bottlenecks for Lung Nodule Malignancy Prediction

arXiv:2608.07857v1 Announce Type: cross Abstract: Foundation models provide transferable CT representations, but predictions based directly on these embeddings are difficult to interpret. We developed

Applications

Distilling Physical Priors into Streaming World Models

arXiv:2608.07981v1 Announce Type: new Abstract: Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts of

applicationsarxiv-cs-cv

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

arXiv:2608.08815v1 Announce Type: new Abstract: Traffic sign recognition (TSR) models based on deep neural networks achieve strong clean-data performance but remain vulnerable to physically realizable

safetyarxiv-cs-lg

Local Ai

DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning

arXiv:2608.09907v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domain

local-aiarxiv-cs-cv

Distributed Optimization with Streaming Data: A Temporal Weighting Perspective

arXiv:2608.09565v1 Announce Type: cross Abstract: Optimization theory is a widely used tool for intelligent decision-making. While classical optimization deals with fixed, time-invariant objective fun

Distribution-Free Conformal Prediction for Steel Fatigue Strength: Marginal Validity Is Not Enough

arXiv:2608.07589v1 Announce Type: cross Abstract: Predicting fatigue failure in steel components experimentally is costly because it requires testing across multiple compositions and processing condit

safetyarxiv-cs-lg

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

arXiv:2608.09047v1 Announce Type: cross Abstract: Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very l

Do AI Forecast Ensembles Sample the Correct Conditional Distribution?

arXiv:2608.08954v1 Announce Type: cross Abstract: Ensemble forecasting aims to sample the conditional distribution of outcomes; whether AI forecast ensembles do this correctly in a joint sense remains

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-

Do Evaluation Metrics Detect Errors in Classical Chinese to English Translations?

arXiv:2608.08283v1 Announce Type: cross Abstract: Although large language models can translate some historical languages surprisingly well, their usefulness in digital humanities workflows is limited

DocAtlas: Long-Document Understanding as Mutable-State Interaction

arXiv:2608.07527v1 Announce Type: cross Abstract: Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-a

DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation

arXiv:2608.09536v1 Announce Type: new Abstract: High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by dive

Does a Toehold Make a Bidder Bolder? Preemption and Multiplicity in Multi-Round Takeover Auctions

arXiv:2608.08407v1 Announce Type: cross Abstract: A bidder can quietly buy a stake in a company before making an offer for it. That stake, a toehold, is supposed to pay for itself twice: it makes the

DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology

arXiv:2608.08148v1 Announce Type: cross Abstract: Attention mechanisms have been widely utilized in modern deep learning, and many existing multi-omics models inherit their conventional use to allow u

Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking

model-releasesarxiv-cs-lg

arXiv:2608.08624v1 Announce Type: new Abstract: Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness

Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

arXiv:2608.09043v1 Announce Type: cross Abstract: Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We

Applications

DoRF++: Spherical Representation Learning over Doppler Radiance Fields for Robust Wi-Fi Sensing

arXiv:2608.08381v1 Announce Type: new Abstract: Motivated by the IEEE 802.11bf effort to standardize advanced WLAN sensing, interest in Wi-Fi Channel State Information (CSI) for passive, device-free,

applicationsarxiv-cs-cv

Doubly Adaptive Channel and Spatial Attention for Semantic Image Communication by IoT Devices

arXiv:2602.22794v2 Announce Type: replace Abstract: Internet of Things (IoT) networks face significant challenges such as limited communication bandwidth, constrained computational and energy resource

researcharxiv-cs-lg

Applications

Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books

arXiv:2608.08349v1 Announce Type: cross Abstract: Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains l

applicationsarxiv-cs-ai

DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models

arXiv:2608.09233v1 Announce Type: cross Abstract: Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-trai

safetyarxiv-cs-cv

Agents

Drone-Assisted UAV-UGV Collaboration for Autonomous Navigation in Snow-Covered Terrain

arXiv:2608.07797v1 Announce Type: cross Abstract: This paper presents a collaborative UAV-UGV navigation framework for high-altitude, snow-covered terrain, where reduced visibility and unstable ground

agentsarxiv-cs-cv

DS@GT ARC at Touche: Large Language Models for Retrieval-Augmented Debate

arXiv:2608.08143v1 Announce Type: cross Abstract: We extend the DS@GT ARC working-note submission to the Touche 2025 Retrieval-Augmented Debate task. The task has two subtasks: generating the next utt

researcharxiv-cs-cl

DSLE: A Learning Environment for Dark Souls Boss Encounters

arXiv:2608.09902v1 Announce Type: new Abstract: We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game

Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

arXiv:2608.09542v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent

DualCert: A Solver for the Traveling Salesman Problem with Constraint-Coupled Learning

arXiv:2608.09042v1 Announce Type: new Abstract: Large traveling salesman problem (TSP) instances require a solver to allocate limited computation while preserving the validity of its outputs. Existing

DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation

arXiv:2608.09637v1 Announce Type: cross Abstract: Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deploymen

Agents

Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

arXiv:2608.07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in adv

agentsarxiv-cs-ai

Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning

arXiv:2608.09011v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Mode

safetyarxiv-cs-lg

Dynamic gain neuromodulation attenuates the stability gap under joint training

arXiv:2507.14056v3 Announce Type: replace-cross Abstract: Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones

Hardware

EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference

arXiv:2608.07964v1 Announce Type: cross Abstract: Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions

hardwarearxiv-cs-ai

eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models

arXiv:2608.08519v1 Announce Type: new Abstract: Intensity-image reconstruction from event streams remains a challenging problem due to the binary, sparse, and asynchronous nature of event data. This w

Hardware

Eco-SoC: A Sustainable VLSI Architecture for Energy-Proportional Artificial Intelligence

arXiv:2608.08761v1 Announce Type: cross Abstract: In an era defined by escalating climate change and the pervasive deployment of edge intelligence, the environmental cost of semiconductor manufacturin

hardwarearxiv-cs-ai

EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding

arXiv:2506.19141v3 Announce Type: replace-cross Abstract: Current electroencephalogram (EEG) decoding models are typically trained on small numbers of subjects performing a single task. Here, we intro

researcharxiv-cs-lg

Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations

arXiv:2608.08085v1 Announce Type: cross Abstract: Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage. These

EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models

arXiv:2608.08138v1 Announce Type: new Abstract: Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increa

safetyarxiv-cs-cv

Local Ai

Efficient Cross-View Localization in 6G Space-Air-Ground Integrated Network

arXiv:2603.11398v2 Announce Type: replace-cross Abstract: Recently, visual localization has become an important supplement to improve localization reliability, and cross-view approaches can greatly en

local-aiarxiv-cs-ai