Search: “models”

AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection

arXiv:2608.07982v1 Announce Type: new Abstract: Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning

Model Releases

AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization

DGX agent

arXiv:2608.07557v1 Announce Type: cross Abstract: Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reactive control in complex 3D environments. Recent minimalist en

model-releasesarxiv-cs-ai

11 Aug 2026

AeroReformer2: Spoken-Query Referring Segmentation for Aerial Images

arXiv:2608.08874v1 Announce Type: new Abstract: Spoken language offers a natural, hands-free interface for specifying an arbitrary target in dense remote-sensing imagery, yet existing referring remote

AI Evaluation Should Measure Verification Cost, Not Correctness Alone

arXiv:2608.08709v1 Announce Type: new Abstract: The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those o

Anchor-Based AI Approach for Pre-Crash Object Detection Utilizing Micro-Doppler Signatures in Automotive Radar

model-releasesarxiv-cs-ro

arXiv:2608.08701v1 Announce Type: new Abstract: Advanced automated driving presents significant potential to improve modern automotive safety systems, but it depends highly on the reliable activation

AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions

arXiv:2506.17455v3 Announce Type: replace Abstract: Robust visual recognition in underwater environments remains a significant challenge due to complex distortions such as turbidity, low illumination,

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

arXiv:2511.19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves t

AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts

arXiv:2601.22758v2 Announce Type: replace Abstract: Large language model agents repeatedly encounter related tasks, yet systems that learn from trajectories commit every lesson to one predefined artif

Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics

arXiv:2608.09638v1 Announce Type: new Abstract: Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reason

Back to the Future: A workbook time machine for spread sheet creation benchmarks

arXiv:2608.07873v1 Announce Type: new Abstract: We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived obj

Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

arXiv:2608.09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expecte

Can Graph Learning Learn Circuits?

arXiv:2608.08536v1 Announce Type: new Abstract: Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient

CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception

arXiv:2608.08392v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven

Circuit Fine-Tuning for Compute-Efficient Transformer Adaptation

arXiv:2608.08336v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become the de facto standard for adapting Vision Transformers (ViTs) to downstream tasks. While parameter cou

Claude will apply invisible watermarks to AI text and images

model-releasesthe-verge-ai

Anthropic has pledged to start marking Claude-generated text and images with machine-readable data, in an effort to comply with European rules for AI transparency. 'Generated text will carry embedded

Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training

arXiv:2608.08224v1 Announce Type: new Abstract: Reinforcement learning post-training unlocks complex reasoning in LLMs. Yet benchmark scores reveal only whether a model improved, not what changed insi

Coupled Graph--Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity

arXiv:2608.09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on

CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

arXiv:2604.03374v2 Announce Type: replace-cross Abstract: Creative problem-solving requires combining multiple cognitive abilities, including logical reasoning, lateral thinking, analogy-making, and c

Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum

arXiv:2504.12742v2 Announce Type: replace Abstract: Decentralized Federated Learning (DFL) enables collaborative model training without relying on a central server. When local objectives are nonconvex

DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO…

model-releasestogether-ai--x

DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO, then deploy the fine-tuned model on Together AI for produc

Depth-Aware Implicit Neural Representation Priors for 3D Gravity Inversion

arXiv:2608.08959v1 Announce Type: new Abstract: Gravimetry images subsurface density contrasts associated with geological structures, geothermal systems, and intrusive bodies. Recovering a three-dimen

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

Efficient Human-Contact Representation for Human-Scene Interaction

arXiv:2608.09388v1 Announce Type: new Abstract: Human-scene interaction is an active research topic with several industrial applications in virtual reality, gaming, robotics, and surveillance. Despite

EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation

model-releasesarxiv-cs-cl

arXiv:2608.07933v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fund

Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis

arXiv:2601.07565v2 Announce Type: replace-cross Abstract: Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while s

Research

From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs

arXiv:2601.17593v3 Announce Type: replace Abstract: Recent progress in large language models has renewed interest in how multi-step reasoning is represented internally. While prior work often treats r

researcharxiv-cs-cl

Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

arXiv:2608.09225v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests.

Research

High-Quality Exposure Correction with Diffusion-Based Image Generation Priors

arXiv:2608.08720v1 Announce Type: new Abstract: Although most existing exposure correction methods achieve high fidelity, they often place excessive focus on overall pixel-wise accuracy, making it cha

researcharxiv-cs-cv

Research

HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

arXiv:2607.18867v2 Announce Type: replace-cross Abstract: Large language models leak parametric knowledge of what followed a historical date into decision tasks indexed by that date -- not necessarily

researcharxiv-cs-cl

Illusion or Integrity? Geometrical Consistency Metric for AIGC Video Quality Evaluation

arXiv:2608.09594v1 Announce Type: cross Abstract: Recently, AI-driven video generation has attracted considerable attention. This surge increases the demand for reliable video quality assessment (VQA)

Local Ai

Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage Analysis

arXiv:2608.08935v1 Announce Type: new Abstract: This work presents a unified multimodal AI system for damage assessment that integrates retrieval-augmented generation (RAG) models, thermal spectrum pe

local-aiarxiv-cs-ai

Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation

model-releasesarxiv-cs-cl

arXiv:2608.07763v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on tasks such as image captioning, visual question answering, and image-to-text generatio

Agents

JaleesBench: Are AI Assistants Good Spiritual Company?

arXiv:2608.07508v1 Announce Type: cross Abstract: Large language models are already advisors to millions of people of faith who bring them real decisions. The pressing question for a person of faith i

agentsarxiv-cs-ai

KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs

arXiv:2608.09779v1 Announce Type: cross Abstract: Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly

Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attribution

arXiv:2608.07943v1 Announce Type: new Abstract: Multi-page visually-rich document understanding (MP-VRDU) requires managing evidence that is sparse, spread across pages, and often exceeds a model's co

Local Ai

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

arXiv:2608.09819v1 Announce Type: cross Abstract: Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after de

local-aiarxiv-cs-cl

Made by Google 2026: all the Pixel news and announcements

model-releasesthe-verge-ai

Google has revealed a bunch of new Pixel devices ahead of its Made by Google event. The colorful Pixel 11 lineup comes with upgraded cameras and performance, with the Pro models offering a built-in LE

Mawqif-v2: An Arabic Benchmark Dataset for Cross-Target Stance Detection

model-releasesarxiv-cs-cl

arXiv:2608.09539v1 Announce Type: new Abstract: Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This pa

Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

arXiv:2608.09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.

MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts

arXiv:2608.09251v1 Announce Type: cross Abstract: Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly

MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design

arXiv:2608.07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet

Multi-Agent Reinforcement Learning via Agent-Specific Preference

arXiv:2608.08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global

Safety

Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks

arXiv:2608.08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure. Su

safetyarxiv-cs-lg

Neural Operators for Immersed-Boundary Soft Swimmers Locomotion

arXiv:2608.07722v1 Announce Type: new Abstract: High-fidelity immersed-boundary simulation resolves the coupled motion of a deforming swimmer and its surrounding flow, but the resulting cost limits re

Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression

arXiv:2608.09176v1 Announce Type: cross Abstract: Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize

Safety

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

arXiv:2608.09931v1 Announce Type: new Abstract: Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Dist

safetyarxiv-cs-cv

Safety

Position Bias in Ordinal Classification: A Systematic Evaluation

arXiv:2608.08869v1 Announce Type: new Abstract: Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predi

safetyarxiv-cs-cl

Local Ai

Position: Certifiable State Integrity Should Be Built from Local Validity, Not Global Scale

arXiv:2601.21249v2 Announce Type: replace Abstract: Breakthroughs in language and vision have motivated increasingly general foundation models for time series and physical dynamics, where evidence is

local-aiarxiv-cs-ai