Papers

New on arXiv

Sat 11 Apr 2026

186 papers

From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic HorizonsDiffusion models → Discrete and text diffusion
STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Taxonomy and Consistency Analysis of Safety Benchmarks for AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMsLLM reasoning → Reinforcement learning for reasoning
The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications AlgorithmsLLM agents and tool use → Agentic AI for wireless networks
Applying an Agentic Coding Tool for Improving Published Algorithm ImplementationsLLM agents and tool use → Web, search, and research agents
Formal Architecture Descriptors as Navigation Primitives for AI Coding AgentsLLM agents and tool use → Software engineering coding agents
Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor ScenariosLLM agents and tool use → Multimodal and embodied agents
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM AgentsLLM agents and tool use → Agent memory systems
WaterAdmin: Orchestrating Community Water Distribution Optimization via AI AgentsLLM agents and tool use → Multimodal and embodied agents
Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided AggregationLLM reasoning → Mathematical reasoning
Zero-shot World Models Are Developmentally Efficient LearnersWorld models → World models for language agents
Jailbreaking the Matrix: Nullspace Steering for Controlled Model SubversionLLM safety and security → Jailbreaking
From Helpful to Trustworthy: LLM Agents for Pair ProgrammingLLM agents and tool use → Software engineering coding agents
Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention HijackingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion DataMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at ScaleLLM reasoning → Time series reasoning
STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion ModelDiffusion models → Image generation, text-to-image and editing
The Amazing Agent Race: Strong Tool Users, Weak NavigatorsLLM agents and tool use → General LLM agent frameworks and benchmarks
A Dual-Positive Monotone Parameterization for Multi-Segment Bids and a Validity Assessment Framework for Reinforcement Learning Agent-based Simulation of Electricity MarketsDeep reinforcement learning methods → RL for energy, networks and operations
Warm-Started Reinforcement Learning for Iterative 3D/2D Liver RegistrationDeep reinforcement learning methods → RL for clinical treatment and surgery
CodeComp: Structural KV Cache Compression for Agentic CodingLLM agents and tool use → Software engineering coding agents +1
Adapting 2D Multi-Modal Large Language Model for 3D CT Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models +1
SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal ReasoningLLM reasoning → Multimodal reasoning
Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning ModelsLLM reasoning → Multimodal reasoning
Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational ContextsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every DecisionLLM agents and tool use → Software engineering coding agents
MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation TasksOffline RL and imitation learning from data → Real-world robot offline RL +1
SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative DecodingMixture-of-experts → Efficient MoE training and inference systems +1
Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's CapabilitiesLLM reasoning → Reasoning benchmarks and evaluation
PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency VerificationLLM agents and tool use → Agent threats, guardrails and governance +1
CircuitSynth: Reliable Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional RewardsDeep reinforcement learning methods → RL training of language and agent models
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled DistillationDiffusion models → Video generation
Ontological Trajectory Forecasting via Finite Semigroup Iteration and Lie Algebra Approximation in Geopolitical Knowledge GraphsLLM reasoning → Test-time compute and efficient thinking
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMsDiffusion models → Diffusion foundations and sampling
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal UncertaintyLLM reasoning → Reinforcement learning for reasoning +1
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination MitigationLLM reasoning → Hallucination detection and mitigation +1
Control of Cellular Automata by Moving Agents with Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
On The Application of Linear Attention in Multimodal TransformersMultimodal LLMs / vision-language models → Visual token pruning and efficiency
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPsDeep reinforcement learning methods → Adversarial robustness and RL in finance
STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal PerturbationsVision-language-action models → Safety and adversarial attacks
HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational RecommendationLLM reasoning → LLM reasoning for recommendation +1
LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache InterventionEfficient LLM inference and serving → KV cache optimization
Intra-finger Variability of Diffusion-based Latent Fingerprint GenerationDiffusion models → Robustness, privacy and adversarial aspects
Counting to Four is still a Chore for VLMsLLM reasoning → Multimodal reasoning
AI Achieves a Perfect LSAT ScoreLLM reasoning → Mathematical reasoning
Closed-Form Concept Erasure via Double ProjectionsDiffusion models → Robustness, privacy and adversarial aspects
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video GenerationDiffusion models → Video generation
Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender SystemsLLM agents and tool use → Agentic recommender systems
LVSum: A Benchmark for Timestamp-Aware Long Video SummarizationMultimodal LLMs / vision-language models → Video understanding with MLLMs
FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial TasksLLM agents and tool use → Financial trading and forecasting agents +1
Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error CorrectionLLM agents and tool use → Financial trading and forecasting agents
Empathic and agentic artificial intelligence in nursing: perspectives on a human-centered framework for cancer care navigation in the United States
MPNet: A Robust and Efficient Manifold Pooling Network for Multi-Rhythm EEG Signal Decoding
SemiConLens: Visual Analytics for 2D Semiconductor Discovery
ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations
AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models
Spike-driven Large Language Model
Full Feature Spiking Neural Network Simulation on Micro-Controllers for Neuromorphic Applications at the Edge
Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge
Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
Inverse Design of Inorganic Compounds with Generative AI
Refined Differentially Private Linear Regression via Extension of a Free Lunch Result
DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
Structural Gating and Effect-aligned Lag-resolved Temporal Causal Discovery Framework with Application to Heat-Pollution Extremes
A Structured Clustering Approach for Inducing Media Narratives
Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
Battery health prognosis using Physics-informed neural network with Quantum Feature mapping
Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
Multi-modal, multi-scale representation learning for satellite imagery analysis just needs a good ALiBi
Context Matters: Vision-Based Depression Detection Comparing Classical and Deep Approaches
VeriTrans: Fine-Tuned LLM-Assisted NL-to-PL Translation via a Deterministic Neuro-Symbolic Pipeline
Integrating SAINT with Tree-Based Models: A Case Study in Employee Attrition Prediction
SIMPLER: H&E-Informed Representation Learning for Structured Illumination Microscopy
From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences
A Diffusion-Contrastive Graph Neural Network with Virtual Nodes for Wind Nowcasting in Unobserved Regions
NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
Comparative Analysis of Large Language Models in Healthcare
Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation
Gypscie: A Cross-Platform AI Artifact Management System
SatReg: Regression-based Neural Architecture Search for Lightweight Satellite Image Segmentation
Class-Adaptive Cooperative Perception for Multi-Class LiDAR-based 3D Object Detection in V2X Systems
AC-MIL: Weakly Supervised Atrial LGE-MRI Quality Assessment via Adversarial Concept Disentanglement
AI Organizations are More Effective but Less Aligned than Individual Agents
Dead Cognitions: A Census of Misattributed Insights
Descriptor-Injected Cross-Modal Learning: A Systematic Exploration of Audio-MIDI Alignment via Spectral and Melodic Features
FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient inference on mobile devices
Dual-Exposure Imaging with Events
The Phase Is the Gradient: Equilibrium Propagation for Frequency Learning in Kuramoto Networks
Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting
A Multi-head Attention Fusion Network for Industrial Prognostics under Discrete Operational Conditions
A Comparison of Multi-View Stereo Methods for Photogrammetric 3D Reconstruction: From Traditional to Learning-Based Approaches
MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training
Exploring the impact of fairness-aware criteria in AutoML

All 186