Search: “models”

Qwen-Image-Flash: Beyond Objective Design

arXiv:2606.03746v1 Announce Type: cross Abstract: Few-step distillation has become an effective strategy for accelerating advanced visual generative models, yet prior work has largely focused on disti

Samudra 2: Scaling Ocean Emulators across Resolutions

arXiv:2606.02610v1 Announce Type: cross Abstract: Ocean general circulation models (OGCMs) are essential to climate science but computationally expensive, limiting ensemble size and forcing scenarios.

model-releasesarxiv-cs-ai

3 Jun 2026

Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data Imputation

arXiv:2606.03517v1 Announce Type: cross Abstract: Training quantum neural networks (QNNs) on quantum hardware is currently bottlenecked by the cost of gradient estimation: standard parameter-shift met

SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding

arXiv:2606.03284v1 Announce Type: new Abstract: Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NL

SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos

arXiv:2606.02745v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) are promising general-purpose robot policies, but adapting them to new tasks typically requires costly task-speci

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation

arXiv:2606.03348v1 Announce Type: cross Abstract: Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic cr

Trading Human Curation for Synthetic Augmentation in RLVR

arXiv:2606.03800v1 Announce Type: cross Abstract: The supply of high-quality training tasks is a central bottleneck for reinforcement learning from verifiable rewards (RLVR) on agentic language models

TriEval: A Resource-Efficient Pipeline for LLM Bias, Toxicity, and Truthfulness Assessment

arXiv:2606.03036v1 Announce Type: new Abstract: LLMs have evolved from basic chatbots to the backbone of the AI ecosystem, now widely used in healthcare, schools, and government services. The domain-w

VidMsg: A Benchmark for Implicit Message Inference in Short Videos

arXiv:2606.03635v1 Announce Type: cross Abstract: Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purp

Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

arXiv:2601.22443v2 Announce Type: replace-cross Abstract: Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard a

researcharxiv-cs-cv

Tutorials

What Do Students Learn? A Feature-Level Analysis of Dark Knowledge

arXiv:2606.03052v1 Announce Type: new Abstract: Knowledge Distillation (KD) is a powerful tool for model compression, yet the precise mechanisms by which student models acquire feature representations

tutorialsarxiv-cs-lg

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing

arXiv:2606.02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-regis

X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

arXiv:2603.05290v2 Announce Type: replace Abstract: Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood. Existing evaluations largely emph

A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation

model-releasesarxiv-cs-cv

arXiv:2606.01973v1 Announce Type: cross Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have m

A Machine-to-Machine Knowledge-Guided LLM Agent for Generalizable Radiotherapy Treatment Planning

model-releasesarxiv-cs-ro

arXiv:2606.00922v1 Announce Type: cross Abstract: In this work, we propose a prototype machine-to-machine (M2M) knowledge-guided Large Language Model (LLM) framework for automated radiotherapy treatme

A unifying Bayesian framework for adversarial robustness

arXiv:2510.09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge. Traditional defenses, such

researcharxiv-cs-lg

Anthropic expands Project Glasswing cybersecurity program to 150 more organizations

model-releasessiliconangle

Anthropic PBC is expanding a program that enables organizations to test their cybersecurity defenses using its Claude Mythos Preview model. The initiative, which is known as Project Glasswing, launche

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition

arXiv:2601.19919v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is one of the most effective paradigms for compressing large-scale foundation models into deployable architectures

Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift

arXiv:2606.02045v1 Announce Type: cross Abstract: Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural

AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Reasoning

arXiv:2606.00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning. In AXIOM, the language model function

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

arXiv:2606.02215v1 Announce Type: new Abstract: Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social p

Beyond Rigid: Benchmarking Non-Rigid Video Editing

model-releasesarxiv-cs-cv

arXiv:2601.18340v2 Announce Type: replace Abstract: As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance f

Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas

arXiv:2603.19453v2 Announce Type: replace Abstract: We study LLM policy synthesis: using a language model to iteratively generate programmatic agent policies for multi-agent environments. Rather than

CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability

arXiv:2606.01495v1 Announce Type: cross Abstract: We present CART (Context-Anchored Recurrent Transformer), a parameter-efficient language model that reuses a single shared core block R times across d

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

arXiv:2603.24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on whi

Codex is becoming a productivity tool for everyone

OpenAI's Codex is evolving beyond code generation to become a general productivity tool accessible to non-programmers for knowledge work tasks. The tool leverages large language models to assist with

model-releasesopenai

Continuous Reasoning for Vision-Language-Action

arXiv:2606.00229v1 Announce Type: cross Abstract: Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?

arXiv:2606.01849v1 Announce Type: cross Abstract: Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data t

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

arXiv:2606.02502v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs

arXiv:2606.00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it

Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs

arXiv:2606.00813v1 Announce Type: cross Abstract: Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with qua

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

arXiv:2606.00931v1 Announce Type: cross Abstract: Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edi

Data Collection for Training Quality-Control AI in Carpet Manufacturing

arXiv:2606.01023v1 Announce Type: cross Abstract: Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at

DenseMLLM: Standard Multimodal LLMs for Dense Prediction

arXiv:2602.14134v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending the

Safety

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

arXiv:2606.00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmfu

safetyarxiv-cs-lg

Safety

DOT-MoE: Differentiable Optimal Transport for MoEfication

arXiv:2606.01666v1 Announce Type: cross Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While

safetyarxiv-cs-ai

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

arXiv:2606.01393v1 Announce Type: cross Abstract: Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Opt

Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

arXiv:2602.03912v4 Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Fo

eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion

arXiv:2606.02054v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical

Applications

Enhancing BiGRU with a KAN Block for Legal Document Classification and Summarization

arXiv:2606.00116v1 Announce Type: cross Abstract: This study introduces a novel architecture of KAN-based BiGRU model for the task of classification and summarization of legal documents in a low-resou

applicationsarxiv-cs-ai

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams

arXiv:2603.27223v2 Announce Type: replace-cross Abstract: We present EuraGovExam, a multilingual and multimodal benchmark sourced from real-world civil service examinations across five representative

FLaG: Fine-Grained Latent Grouping for Hallucination Detection

arXiv:2606.00301v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global un

researcharxiv-cs-lg

Flow Matching for Convective-Scale Precipitation Downscaling

arXiv:2606.00281v1 Announce Type: cross Abstract: Generative machine learning is an increasingly important complement to dynamical downscaling for producing high-resolution precipitation projections,

Local Ai

Flux klein 9b Comic Character Lora?

local-air-stablediffusion

This post discusses creating or using a LoRA (Low-Rank Adaptation) model compatible with Flux Klein 9b, an AI image generation model, specifically for generating comic book-style characters. The discu

From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures

arXiv:2602.04861v2 Announce Type: replace-cross Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (P

From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication

arXiv:2606.01136v1 Announce Type: new Abstract: Single-score translation metrics can conflate legitimate variation with error, a problem especially acute for classical languages where multiple defensi

GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation

model-releasesarxiv-cs-cv

arXiv:2606.00886v1 Announce Type: new Abstract: Accurate segmentation is crucial for autonomous spacecraft, as it directly affects downstream tasks related to 3D situational awareness. The harsh illum

GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning

arXiv:2605.13136v2 Announce Type: replace Abstract: Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales,

researcharxiv-cs-cl