Papers

New on arXiv

Sat 24 Jan 2026

175 papers

Turbo4DGen: Ultra-Fast Acceleration for 4D GenerationWorld models → Video-generation world models and simulators
Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference OptimizationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
A Lightweight Explainable Guardrail for Prompt SafetyLLM safety and security → Safety alignment, refusal and guardrails
Denoising diffusion networks for normative modeling in neuroimagingDiffusion models → Medical imaging and segmentation
GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-TrainingLLM reasoning → Knowledge- and tool-augmented reasoning
Mirage2Matter: A Physically Grounded Gaussian World Model from VideoWorld models → Video-generation world models and simulators
Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull RequestsLLM agents and tool use → Software engineering coding agents
BrainDistill: Implantable Motor Decoding with Task-Specific Knowledge DistillationKnowledge distillation → Distillation for medical imaging
Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search RequestsLLM agents and tool use → Web, search, and research agents
Athena: Synergizing Data Prefetching and Off-Chip Prediction via Online Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
AlignUI: A Method for Designing LLM-Generated UIs Aligned with User PreferencesLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Deep Intrinsic Surprise-Regularized Control (DISRC): A Biologically Inspired Mechanism for Efficient Deep Q-Learning in Sparse EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull RequestsLLM agents and tool use → Software engineering coding agents
Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO OptimizationDeep reinforcement learning methods → Quantum reinforcement learning
Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated SpeculationsRetrieval-augmented generation → Privacy and security of RAG
Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour AlignmentOffline RL and imitation learning from data → Imitation learning methods
Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol EcosystemsLLM agents and tool use → Agent threats, guardrails and governance +1
Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary QueriesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence SelectionRetrieval-augmented generation → Generation and context integration
MetaWorld: Skill Transfer and Composition in a Hierarchical World Model for Grounding High-Level InstructionsWorld models → Humanoid and legged locomotion world models
SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-SolvingLLM reasoning → Spatial and embodied reasoning
EquiForm: Noise-Robust SE(3)-Equivariant Policy Learning from 3D Point CloudsOffline RL and imitation learning from data → Robot manipulation imitation learning
Lattice: Generative Guardrails for Conversational AgentsLLM safety and security → Safety alignment, refusal and guardrails
PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability RepairLLM agents and tool use → Software engineering coding agents
Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation ShapingLLM reasoning → Hallucination detection and mitigation
Towards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server EcosystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
A Syllogistic Probe: Tracing the Evolution of Logic Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Oops, Wait: Discourse Tokens Matter in Reasoning ModelLLM reasoning → Test-time compute and efficient thinking
CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-CorrectionLLM reasoning → Multimodal reasoning
GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge GraphLLM reasoning → Multimodal reasoning +1
DiffusionCinema: Text-to-Aerial CinematographyDiffusion models → Diffusion and flow policies for robotics
Fingerprinting AI Coding Agents on GitHubLLM agents and tool use → Software engineering coding agents
ONRW: Optimizing inversion noise for high-quality and robust watermarkDiffusion models → Robustness, privacy and adversarial aspects
Physical Prompt Injection Attacks on Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning ModelsLLM safety and security → Federated unlearning and poisoning
Diversified Scaling Inference in Time Series Foundation ModelsLLM reasoning → Diffusion reasoning and test-time scaling
Auditing Disability Representation in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Multi-Agent Learning Path Planning via LLMsLLM agents and tool use → Educational agents and math problem solving
The Shadow Self: Intrinsic Value Misalignment in Large Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-ResolutionDiffusion models → Inverse problems and image restoration
TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic WorkflowLLM agents and tool use → Educational agents and math problem solving +1
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
SkyReels-V3 Technique ReportWorld models → Video-generation world models and simulators +1
Phase Transition for Budgeted Multi-Agent SynergyLLM agents and tool use → General LLM agent frameworks and benchmarks
Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
The Viscosity of Logic: Phase Transitions and Hysteresis in DPO AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Inference-Time Loss-Guided Colour Preservation in Diffusion SamplingDiffusion models → Image generation, text-to-image and editing
Learning Market Making with Closing AuctionsDeep reinforcement learning methods → Adversarial robustness and RL in finance
Unbiased Rectification for Sequential Recommender Systems Under Fake Orders
Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA
Generating Counterfactual Patient Timelines from Real-World Data
From Prompts to Worlds: How Users Iterate, Explore, and Make Sense of AI-Generated 3D Environments
Lost in Translation: How Language Re-Aligns Vision for Cross-Species Pathology
Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systems
Building Safe and Deployable Clinical Natural Language Processing under Temporal Leakage Constraints
Artificial Intelligence for Inclusive Engineering Education: Advancing Equality, Diversity, and Ethical Leadership
Evaluation of Large Language Models' educational feedback in Higher Education: potential, limitations and implications for educational practice
What Drives Length of Stay After Elective Spine Surgery? Insights from a Decade of Predictive Modeling
Radiomics in Medical Imaging: Methods, Applications, and Challenges
Frequent Pattern Mining approach to Image Compression
Gauss-Newton Natural Gradient Descent for Shape Learning
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization
Lossy Image Compression -- A Frequent Sequence Mining perspective employing efficient Clustering
Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant
Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning
ToS: A Team of Specialists ensemble framework for Stereo Sound Event Localization and Detection with distance estimation in Video
What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization
A Thermodynamic Theory of Learning I: Irreversible Ensemble Transport and Epistemic Costs
Human-Aligned Enhancement of Programming Answers with LLMs Guided by User Feedback
Understanding Transformer Encoder-Decoder Representations through Bernoulli Dropout
Learning to Ideate for Machine Learning Engineering Agents
Intelligence Requires Grounding But Not Embodiment
Discovery of Feasible 3D Printing Configurations for Metal Alloys via AI-driven Adaptive Experimental Design
Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization
Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models
Prompt Driven Development with Claude Code: Building a Complete TUI Framework for the Ring Programming Language
GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design
Status Hierarchies in Language Models
ME-WARD: A multimodal ergonomic analysis tool for musculoskeletal risk assessment from inertial and video data in working plac
Real-Time Trend Prediction via Continually-Aligned LLM Query Generation
JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research
Sparse RBF Networks for PDEs and nonlocal equations: function space theory, operator calculus, and training algorithms
Saliency Driven Imagery Preprocessing for Efficient Compression -- Industrial Paper
GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference
In-situ On-demand Digital Image Correlation: A New Data-rich Characterization Paradigm for Deformation and Damage Development in Solids
Cognitive Platform Engineering for Autonomous Cloud Operations
OTI: A Model-free and Visually Interpretable Measure of Image Attackability
Reconstructing Training Data from Adapter-based Federated Large Language Models
Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes
FMIR, a foundation model-based Image Registration Framework for Robust Image Registration
Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework
EuleroDec: A Complex-Valued RVQ-VAE for Efficient and Robust Audio Coding
One-Shot Federated Clustering of Non-Independent Completely Distributed Data
"Rebuilding" Statistics in the Age of AI: A Town Hall Discussion on Culture, Infrastructure, and Training

All 175