Search: “models”

Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design

arXiv:2605.19717v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead

Safety

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

DGX agent

arXiv:2605.19220v1 Announce Type: cross Abstract: Uncertainty Quantification (UQ) is widely regarded as the primary safeguard for deploying Large Language Models (LLMs) in high-stakes domains. However

safetyarxiv-cs-ai

20 May 2026

PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling

arXiv:2605.20052v1 Announce Type: cross Abstract: Automatic report labeling facilitates the identification of clinical findings from unstructured text and enables large-scale annotation for medical im

RECIPE: Procedural Planning via Grounding in Instructional Video

arXiv:2605.19976v1 Announce Type: new Abstract: Visual planning asks a model to generate the remaining steps of a procedure in natural language given a partial video context and a goal. Progress on th

Retrieval-Augmented Generation for Natural Language Processing: A Survey

arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that stor

Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions

arXiv:2605.19823v1 Announce Type: cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently contin

Applications

Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

arXiv:2505.23747v2 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving

applicationsarxiv-cs-ai

Tail Annealing for Heavy-Tailed Flow Matching

arXiv:2605.20068v1 Announce Type: cross Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolat

Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning

arXiv:2605.19358v1 Announce Type: new Abstract: Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing

Safety

TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting

arXiv:2605.18843v1 Announce Type: new Abstract: Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet mod

safetyarxiv-cs-lg

The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints

arXiv:2605.19066v1 Announce Type: new Abstract: Over the past decade, low-resource natural language processing (NLP) has experienced explosive growth, propelled by cross-lingual transfer, massively mu

The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measur…

model-releasesclem-delangue--x

The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measuring every biomarker, or @sytses openly sharing and analyzing

The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility

arXiv:2605.19537v1 Announce Type: new Abstract: Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a per

Towards Consistent Detection of Cognitive Distortions: LLM-Based Annotation and Dataset-Agnostic Evaluation

arXiv:2511.01482v2 Announce Type: replace Abstract: Text-based automated Cognitive Distortion detection is a challenging task due to its subjective nature, with low agreement scores observed even amon

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

arXiv:2605.18859v1 Announce Type: cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user reque

What Do Evolutionary Coding Agents Evolve?

arXiv:2605.20086v1 Announce Type: cross Abstract: Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have prod

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection

arXiv:2601.22569v2 Announce Type: replace-cross Abstract: Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning e

A Feature-Driven Framework for Software Fault Prediction

arXiv:2605.17611v1 Announce Type: cross Abstract: Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software qua

A Machine With Human-Like Memory Systems

arXiv:2204.01611v3 Announce Type: replace Abstract: Inspired by the cognitive science theory, we explicitly model an agent with both semantic and episodic memory systems, and show that it is better th

Research

A Theory of Training Profit-Optimal LLMs

arXiv:2605.16430v1 Announce Type: cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure

researcharxiv-cs-ai

Local Ai

AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training

arXiv:2605.17923v1 Announce Type: cross Abstract: In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant com

local-aiarxiv-cs-ai

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory

arXiv:2605.18733v1 Announce Type: new Abstract: Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory

Agents

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

arXiv:2602.03955v2 Announce Type: replace Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limite

agentsarxiv-cs-ai

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech

arXiv:2605.17583v1 Announce Type: new Abstract: While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the

AgentWall: A Runtime Safety Layer for Local AI Agents

arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active ac

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

arXiv:2603.23069v2 Announce Type: replace-cross Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original tex

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

arXiv:2510.00304v3 Announce Type: replace-cross Abstract: Deep learning models excel in stationary data but struggle in non-stationary environments due to a phenomenon known as loss of plasticity (LoP

Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs

arXiv:2602.09805v2 Announce Type: replace-cross Abstract: As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no lon

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

arXiv:2603.00876v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical

Research

CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth

arXiv:2605.16736v1 Announce Type: new Abstract: Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. E

researcharxiv-cs-cv

Can’t wait for Gemini Omni in @NotebookLM cinematic explainer videos 👀

model-releasesemad-mostaque--x

Emad Mostaque expressed anticipation for the integration of Google's Gemini Omni multimodal AI model into NotebookLM's cinematic explainer video generation features. The post suggests potential upcomi

CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning

arXiv:2605.17176v1 Announce Type: new Abstract: Emotion understanding is a core capability for LLMs to interact effectively with humans, yet existing evaluation paradigms rely on discrete emotion labe

ClawArena: Benchmarking AI Agents in Evolving Information Environments

arXiv:2604.04202v2 Announce Type: replace-cross Abstract: AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is s

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

arXiv:2605.16839v1 Announce Type: new Abstract: Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime

ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse

arXiv:2605.17450v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for automated vulnerability repair (AVR), where repository-level reasoning enables them to ins

Agents

DECODE: Domain-aware Continual Domain Expansion for Motion Prediction

arXiv:2411.17917v2 Announce Type: replace Abstract: Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other

agentsarxiv-cs-cv

Local Ai

Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation

arXiv:2605.18395v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit systematic political biases in voter simulations, but their underlying mechanisms and cross-lingual generalizatio

local-aiarxiv-cs-ai

Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations

arXiv:2605.17107v1 Announce Type: cross Abstract: We introduce a novel framework for uncertainty quantification of solution operators associated with stochastic partial differential equations (SPDEs).

DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes

arXiv:2601.13839v2 Announce Type: replace Abstract: Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage asse

Safety

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning

arXiv:2405.19189v3 Announce Type: replace Abstract: With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential i

safetyarxiv-cs-lg

Evaluating Cognitive Age Alignment in Interactive AI Agents

arXiv:2605.17894v1 Announce Type: new Abstract: While agentic AI and its core multimodal large language models (MLLMs) have demonstrated remarkable promise in language and visual reasoning across doma

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

arXiv:2511.20857v2 Announce Type: replace-cross Abstract: Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critica

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

arXiv:2605.18421v1 Announce Type: cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agen

Experimentally validated quantum-secure federated learning over a multi-user quantum network

arXiv:2501.12709v2 Announce Type: replace-cross Abstract: Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum fe

exttt{SynC}: Synergistic Boosting of Structure and Representation for Deep Graph Clustering

arXiv:2406.15797v2 Announce Type: replace-cross Abstract: Employing graph neural networks (GNNs) for graph clustering has shown promising results in deep graph clustering. However, existing methods di

Fine-grained List-wise Alignment for Generative Medication Recommendation

arXiv:2505.20218v2 Announce Type: replace Abstract: Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, exist

Research

Flowing with Confidence

arXiv:2605.18472v1 Announce Type: cross Abstract: Generative models can produce nonsensical text, unrealistic images, and unstable materials faster than simulation or human review can absorb; without

researcharxiv-cs-ai

Applications

From Documents to Segments: A Contextual Reformulation for Topic Assignment

arXiv:2605.17714v1 Announce Type: new Abstract: Traditional topic modeling assigns a single topic to each document. In practice, however, many real-world documents, such as product reviews or open-end

applicationsarxiv-cs-cl