Search: “models”

arXiv:2602.09708v2 Announce Type: replace-cross Abstract: We propose physics-informed spectral diffusion (PISD), a methodology that combines generative latent diffusion models with physics-informed ma

tutorialsarxiv-cs-ai

Post-Hoc Robustness for Model-Based Reinforcement Learning

DGX agent

arXiv:2606.03521v1 Announce Type: cross Abstract: To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversa

safetyarxiv-cs-ai

3 Jun 2026

Applications

Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation

arXiv:2508.03098v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sou

applicationsarxiv-cs-cl

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory

arXiv:2511.16275v4 Announce Type: replace-cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables t

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression

arXiv:2602.17063v2 Announce Type: replace-cross Abstract: Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-co

Social Caption: Evaluating Social Understanding in Multimodal Models

arXiv:2601.14569v2 Announce Type: replace Abstract: Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL

researcharxiv-cs-cl

The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models

arXiv:2606.02867v1 Announce Type: cross Abstract: Human behaviour during epidemics affects infectious disease dynamics, but quantifying this remains deeply challenging. Here we introduce the Epi-LLM f

agentsarxiv-cs-ai

The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models

arXiv:2606.03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.

TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models

arXiv:2606.03127v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at depl

safetyarxiv-cs-ro

Tutorials

Your Autoregressive Model Already Reveals the Causal Graph

arXiv:2602.01135v3 Announce Type: replace Abstract: Autoregressive models trained via next-token prediction implicitly learn the conditional independence structure of their data-generating process. We

tutorialsarxiv-cs-lg

A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models

arXiv:2601.17952v2 Announce Type: replace-cross Abstract: Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer di

Tutorials

AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations

arXiv:2508.17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoenc

tutorialsarxiv-cs-lg

Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning

arXiv:2606.01558v1 Announce Type: new Abstract: The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain: across several visual reasoning ben

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models

model-releasesarxiv-cs-ai

arXiv:2606.01961v1 Announce Type: new Abstract: Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form c

Belief Consistency Between Foundation-Model Evidence and Geometric Perception in Persistent Robotic Maps

arXiv:2606.00318v1 Announce Type: cross Abstract: Persistent maps used by autonomous robots increasingly fuse a geometric perception stack whose assertions are well-characterized with a foundation-mod

agentsarxiv-cs-cv

Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design

arXiv:2507.15336v3 Announce Type: replace-cross Abstract: Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail

Beyond Pure Sampling: Hybrid Optimization Mechanisms for Non-Convex Model Predictive Control

arXiv:2606.00737v1 Announce Type: new Abstract: This paper investigates the optimization mechanisms of non-convex Model Predictive Control (MPC) using the Maximum Entropy Differential Dynamic Programm

local-aiarxiv-cs-ro

Bridging Topology and Deep Representation Learning: A TDA-ViT Fusion Model for Four-Class Brain Tumor Classification

arXiv:2606.00927v1 Announce Type: new Abstract: Accurate brain tumor classification from magnetic resonance imaging (MRI) is a key requirement for early diagnosis and clinical decision-making. Vision

Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings

arXiv:2606.00426v1 Announce Type: new Abstract: Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text. Under user-level

Challenges in the calibration of tree-based models for imbalanced classification

arXiv:2412.16209v5 Announce Type: replace Abstract: When using machine learning for imbalanced binary classification problems, it is common to subsample the majority class to create a (more) balanced

safetyarxiv-cs-lg

Closed-Loop Neural Activation Control in Vision-Language-Action Models

arXiv:2606.00269v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

arXiv:2606.02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robot

safetyarxiv-cs-lg

Cross-modal linkage risk in clinical vision-language models

arXiv:2606.02276v1 Announce Type: cross Abstract: Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-leve

Detect Before You Leap: Mirage Detection in Vision-Language Models

arXiv:2606.00435v1 Announce Type: cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the quest

Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games

model-releasesarxiv-cs-ai

arXiv:2606.00103v1 Announce Type: new Abstract: We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Where

Applications

From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generation

arXiv:2606.02167v1 Announce Type: new Abstract: Engineers designing production systems need to verify that a given layout supports all required production sequences. Automated planning techniques can

applicationsarxiv-cs-ai

Industry

@garrytan Model, application, and infrastructure layers trying to commoditize each other

This post discusses how the model, application, and infrastructure layers of AI are competing to commoditize each other, suggesting a dynamic where each layer is attempting to move upstream or downstr

industrysonya-huang--x

Generative Multi-Robot Motion Planning via Diffusion Modeling with Multi-Agent Reinforcement Learning Guidance

arXiv:2606.00933v1 Announce Type: new Abstract: Coordinating multiple robots in shared environments requires generating feasible trajectories for each agent while accounting for interactions among age

agentsarxiv-cs-ro

Hoeffding Concept Bottleneck Models with Applications to Overhead Images

arXiv:2606.00082v1 Announce Type: cross Abstract: Explainability of deep learning algorithms is critical for computer-vision applications with high-stake decisions. Concept bottleneck models (CBM) hav

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families

arXiv:2606.02231v1 Announce Type: cross Abstract: Temporal systems often exhibit non-stationary behaviour, such as seasonal climate variation or glucose fluctuations in patients with type-1 diabetes.

iLRM: An Iterative Large 3D Reconstruction Model

arXiv:2507.23277v3 Announce Type: replace Abstract: Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explic

Applications

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models

arXiv:2606.02161v1 Announce Type: cross Abstract: Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial comput

applicationsarxiv-cs-cl

Language-Native Materials Processing Design by Lightly Structured Text Database and Reasoning Large Language Model

model-releasesarxiv-cs-ai

arXiv:2509.06093v4 Announce Type: replace-cross Abstract: Materials synthesis procedures are predominantly documented as narrative text in papers, protocols, and laboratory records, placing them beyon

Hardware

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

arXiv:2606.01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) an

hardwarearxiv-cs-ai

Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model

arXiv:2606.01698v1 Announce Type: new Abstract: Deep learning has revolutionized medical image analysis, delivering exceptional diagnostic accuracy across diverse applications. Yet, the lack of interp

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models

arXiv:2602.03211v2 Announce Type: replace-cross Abstract: Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent. This

LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models

arXiv:2603.00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards 'Thinking with Images' by actively exploring image details. While effective, lar

local-aiarxiv-cs-ai

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning

model-releasesarxiv-cs-cl

arXiv:2606.01301v1 Announce Type: new Abstract: Hallucinations in medical large language models (LLMs) pose serious risks for clinical decision support, particularly when models must reason over compl

Microsoft debuts an expansion of its model families and agentic AI intelligence for developers

Microsoft Corp. announced an expansion to its artificial intelligence models and agentic AI infrastructure today that brings more data and context into the hands of developers and business users as th

agentssiliconangle

Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping

arXiv:2606.00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

arXiv:2606.00909v1 Announce Type: cross Abstract: This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations within Multimodal Large Language Models (MLLMs).

Modeling Distinct Human Interaction in Web Agents

arXiv:2602.17588v3 Announce Type: replace Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks

agentsarxiv-cs-cl

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

arXiv:2503.07325v2 Announce Type: replace Abstract: Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning. We introduce

local-aiarxiv-cs-lg

Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation

arXiv:2606.00253v1 Announce Type: cross Abstract: Fine-tuning Vision-Language-Action (VLA) models for mobile manipulators with heterogeneous joint spaces can produce a counterintuitive result: the che

Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning

model-releasesarxiv-cs-lg

arXiv:2606.00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful i

Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial

arXiv:2606.00935v1 Announce Type: new Abstract: We test whether a relational-style intervention delivered during functional collapse in a small language model produces post-collapse behavior distingui

local-aiarxiv-cs-ai

SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models

model-releasesarxiv-cs-ro

arXiv:2606.00773v1 Announce Type: new Abstract: Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety-relevant tr

Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

arXiv:2606.01340v1 Announce Type: new Abstract: We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of t