Search: “models”

A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction

arXiv:2608.14750v1 Announce Type: cross Abstract: Left ventricular ejection fraction (LVEF) estimation (Task 1), global longitu-dinal strain (GLS)-based dysfunction classification (Task 2), and early

Model Releases

Aborted but Not Forgotten: KV-Cache Retention Breaks Rollback Consistency in Language Agents

DGX agent

arXiv:2608.15939v1 Announce Type: new Abstract: Stateful language agents assume a rejected branch can be taken back by clearing it from the application transcript. We show this breaks when the serving

model-releasesarxiv-cs-cl

18 Aug 2026

Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots

model-releasesarxiv-cs-ro

arXiv:2608.16030v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate textual robot design specifications, interaction policies, and risk assessments during ea

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

arXiv:2608.16196v1 Announce Type: new Abstract: Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this infer

Characterization of Thermal Systems from Noisy and Low-resolution Measurements Using Dynamic Mode Decomposition

arXiv:2608.14581v1 Announce Type: cross Abstract: Thermal monitoring in practical applications is often constrained by sparse sensing, measurement noise, and limited spatial resolution, which hinder t

Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles

arXiv:2608.16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monit

researcharxiv-cs-lg

DeepInsight II: One Trace from Benchmark to Robot

arXiv:2608.16556v1 Announce Type: new Abstract: Across a Physical AI stack, evaluation maturity is inversely aligned with deployment risk: foundation models enjoy mature, standardized harnesses, while

Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection

arXiv:2608.16259v1 Announce Type: cross Abstract: The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliab

DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis

arXiv:2603.23924v2 Announce Type: replace Abstract: Text-to-image models often struggle to synthesize correct occlusion relationships among multiple objects, especially in densely overlapping regions.

Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

arXiv:2608.14808v1 Announce Type: new Abstract: When a user question is underspecified, a capable model should recognize that its context is insufficient, identify the missing information, ask for it,

researcharxiv-cs-ai

Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics

arXiv:2608.16084v1 Announce Type: new Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error g

safetyarxiv-cs-ai

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

arXiv:2608.15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and

FusionBERT: Multi-View Image--3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder

arXiv:2604.02583v2 Announce Type: replace Abstract: We propose FusionBERT, a novel multi-view visual fusion framework for image--3D multimodal retrieval. Existing image--3D representation learning met

safetyarxiv-cs-cv

Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance

arXiv:2608.16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task. We ask whether it finished it within policy. We introduce Fiducia-bench, a benchmark

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

arXiv:2608.16859v1 Announce Type: new Abstract: A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially

Incoherent by Design? On the Moral Self-Consistency of LLMs

arXiv:2608.15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A mode

INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval

arXiv:2608.16203v1 Announce Type: cross Abstract: Existing speech retrieval systems rely on fixed similarity matching and cannot adapt to diverse user intents. We introduce INSPIRE, the first benchmar

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

arXiv:2506.07449v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG)

LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks

arXiv:2608.14927v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collabora

MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration

arXiv:2601.23049v2 Announce Type: replace Abstract: Medical calculators are fundamental to quantitative, evidence-based clinical practice. However, their real-world use is an adaptive, multi-stage pro

MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter

arXiv:2608.16709v1 Announce Type: cross Abstract: A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readab

researcharxiv-cs-ai

Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank

arXiv:2602.02414v2 Announce Type: replace Abstract: Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

arXiv:2505.21333v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, the

Muse Glimmer 30B is now available on Fireworks' Dedicated Training API for both LoRA and Full-Parameter fine-tuning. This is a U.S.-develope…

model-releasesfireworks-ai--x

Muse Glimmer 30B is now available on Fireworks' Dedicated Training API for both LoRA and Full-Parameter fine-tuning. This is a U.S.-developed, open-weight model and one of the strongest of its size fo

Neurosymbolic Embodied Agents

arXiv:2608.16794v1 Announce Type: cross Abstract: Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dyn

safetyarxiv-cs-ai

Local Ai

Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

arXiv:2608.15115v1 Announce Type: new Abstract: Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transfe

local-aiarxiv-cs-cv

Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

arXiv:2608.16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a f

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

arXiv:2608.16003v1 Announce Type: new Abstract: Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring

researcharxiv-cs-ai

PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

arXiv:2603.08590v3 Announce Type: replace Abstract: Text-to-motion generation has advanced with larger corpora and stronger generators, yet many models still rely on holistic frame- or clip-level late

Applications

Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy

arXiv:2509.10691v3 Announce Type: replace-cross Abstract: Decentralized federated learning enables collaborative model training without a central server, but shared model updates can still leak sensit

applicationsarxiv-cs-ai

Revisiting the Performance of Generative Artificial Intelligence on Introductory Object-Oriented Programming Assessments: Insights from 2026

arXiv:2608.16318v1 Announce Type: cross Abstract: Recent advances in Generative Artificial Intelligence (GenAI) have substantially improved the ability of large language models (LLMs) to generate and

ROC-n-reroll: How verifier imperfection affects test-time scaling

arXiv:2507.12399v3 Announce Type: replace Abstract: Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied

Running DeepSeek V4 Flash Q4_K_XL at ~100 tok/s prompt processing on 4× RTX 3060 12GB

model-releasesr-localllama

I managed to run the 143–144 GiB DeepSeek-V4-Flash-0731 UD-Q4_K_XL GGUF on four RTX 3060 12GB cards while keeping a 360k–376k context window. Hardware: CPU: Intel Core i9-10920X, 12C/24T RAM: 128 GB D

S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices

arXiv:2608.15018v1 Announce Type: new Abstract: Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative de

Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning

arXiv:2303.07152v3 Announce Type: replace-cross Abstract: Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data an

Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline

arXiv:2608.16187v1 Announce Type: cross Abstract: AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify sec

Sharing a new way to work with Stable Audio

model-releasesstability-ai

Stable Audio 3.0 now offers a DAW‑plugin that brings real‑time audio generation directly into your favorite digital audio workstation, letting you arrange, edit, and mix generated tracks like any othe

StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

arXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate

Sterilizable Scene Graph Generation for Operating Rooms

arXiv:2608.16469v1 Announce Type: new Abstract: Scene graph generation from surgical video enables a holistic and structured understanding of surgical scenes by modeling objects and their semantic rel

SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates

arXiv:2608.15665v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance grad

Tutorials

SUGFW+: An Uncertainty-guided Feature Weighting Framework for Cold Start Active Adaptation of SAM in Medical Image Segmentation

arXiv:2608.16110v1 Announce Type: new Abstract: Cold Start Active Learning (CSAL) is important in improving the performance of a medical image segmentation model with low annotation budget by querying

tutorialsarxiv-cs-cv

TDD-Agent: Test-Driven Reasoning for Code Generation

arXiv:2608.16742v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains

The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks

arXiv:2608.16096v1 Announce Type: cross Abstract: Enterprises connect language models to their own data through retrieval. The benchmarks that rank multi-hop retrieval systems leave out two facts a bu

Agents

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

arXiv:2608.16775v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making a

agentsarxiv-cs-ai

Local Ai

TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH

arXiv:2608.16410v1 Announce Type: new Abstract: Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparam

local-aiarxiv-cs-lg

Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis

arXiv:2608.16379v1 Announce Type: new Abstract: Evaluating speech recognition for a Kurdish variety written in a Latin field orthography, using a model that outputs Arabic script, creates a measuremen

ViTaR: Visuo-Tactile Residual Adaptation for Foundation VLA Manipulation

model-releasesarxiv-cs-ro

arXiv:2608.15816v1 Announce Type: new Abstract: As Vision-Language-Action (VLA) models scale toward real-world deployment, contact-rich manipulation exposes a critical blind spot: these policies encod

When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

arXiv:2608.16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context

safetyarxiv-cs-ai