4/13/2026
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
RAG systems should optimize for utility (task completion) rather than topical relevance when retrieving documents for LLMs.
4/13/2026
MuTSE: A Human-in-the-Loop Multi-use Text Simplification Evaluator
MuTSE: Human-in-the-loop evaluator tool for systematically comparing LLM text simplification outputs across different prompting strategies and architectures.
4/13/2026
WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning
WOMBET: Framework for reinforcement learning that generates and transfers experience data between source and target robotic tasks for sample efficiency.
4/13/2026
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
Aligned Agents, Biased Swarm: Empirical study measuring how multi-agent system topologies and feedback loops amplify bias in emergent behaviors.
4/13/2026
Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models
Litmus ReAgent: Benchmark and agentic system for evaluating multilingual LLM performance prediction across 1,500 questions spanning six tasks and five evidence scenarios.
4/13/2026
PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
PerMix-RLVR: Training method for aligning LLM personas with reward models while preserving output diversity, avoiding inference-time computation overhead.
4/13/2026
PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
PinpointQA dataset and benchmark for evaluating small object localization and spatial reasoning in video MLLMs.
4/13/2026
ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
ASTRA: adaptive semantic tree reasoning architecture for LLM-based complex table question answering.
4/13/2026
Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
Regime-conditional retrieval with transferable router for two-hop question answering with theoretical foundations.
4/13/2026
Noise-Aware In-Context Learning for Hallucination Mitigation in ALLMs
Noise-aware in-context learning approach to mitigate hallucinations in auditory large language models.
4/13/2026
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
ImageProtector prevents multi-modal LLMs from analyzing images via visual prompt injection attacks.
4/13/2026
Skill-Conditioned Visual Geolocation for Vision-Language
Vision-language models for image geolocation with structured geographic reasoning and autonomous self-evolution.
4/13/2026
CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space
CONDESION-BENCH evaluates LLM decision-making with compositional action spaces and conditional feasibility constraints.
4/13/2026
Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
Watt Counts: open-access energy consumption benchmark for LLM inference across 50 models and 10 GPU architectures.
4/13/2026
PDE-regularized Dynamics-informed Diffusion with Uncertainty-aware Filtering for Long-Horizon Dynamics
PDYffusion combines diffusion models with physics-informed dynamics for long-horizon spatiotemporal prediction.
4/13/2026
Learning Vision-Language-Action World Models for Autonomous Driving
Vision-Language-Action models for autonomous driving combining perception, reasoning, and temporal dynamics modeling.
4/13/2026
Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models
Method integrating graph-based embeddings into event sequence models for improved user prediction on digital platforms.
4/13/2026
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
DeepGuard improves secure code generation by LLMs through multi-layer semantic aggregation to mitigate vulnerable patterns.
4/13/2026
CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
CLIP-Inspector detects backdoor attacks in prompt-tuned vision-language models through out-of-distribution trigger inversion.
4/13/2026
Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence
Research on detecting covert misaligned AI behavior in real-world settings using open-source intelligence methods.
4/13/2026
TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training
TensorHub introduces Reference-Oriented Storage for efficient weight transfer in LLM reinforcement learning across heterogeneous computational resources.
4/13/2026
PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing
PS-TTS method for phonetic synchronization in automated dubbing, addressing duration and lip-sync challenges in AI-based video translation.
4/13/2026
Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition
Interactive ASR system with human-like interaction and semantic coherence evaluation, replacing WER metric with agent-based correction mechanisms.
4/13/2026
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
EquiformerV3: SE(3)-equivariant graph attention Transformer for 3D atomistic modeling, improving efficiency, expressivity, and physical consistency.
4/13/2026
CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
CORA framework for risk-controlled GUI automation agents using conformal prediction to provide formally verified, user-tunable safety guarantees for VLM-powered mobile automation.
4/13/2026
Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning
LLM-based agents for scaffolding diagnostic reasoning in educational settings, combining scenario-based learning with learning analytics and personalized support.
4/13/2026
Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events
Dataset for personality-shaped emotional responses to text events, addressing limitations of LLM role-playing and personality illusion in affective computing.
4/13/2026
Generalization and Scaling Laws for Mixture-of-Experts Transformers
Theoretical analysis of generalization and scaling laws for Mixture-of-Experts Transformers, separating active capacity from routing combinatorics with covering-number bounds.
4/13/2026
Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies
Symbolic-Neural Consistency Audit framework extracting and formalizing LLM self-stated safety policies.
4/13/2026
On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach
GNN-based deep reinforcement learning scheduler for cloud workflow DAG assignment minimizing time and energy.
4/13/2026
GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
GRM gradient-ratio masking attack on audio LLMs balancing jailbreak success with utility preservation.
4/13/2026
Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
Mosaic multimodal jailbreak attack against closed-source VLMs via multi-view ensemble optimization.
4/13/2026
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
SkillMOO multi-objective optimization framework automatically evolving agent skill bundles for coding tasks.
4/13/2026
Visually-Guided Policy Optimization for Multimodal Reasoning
Visually-guided policy optimization improving visual faithfulness in vision-language models via reinforcement learning.
4/13/2026
LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation
LLM-Rosetta hub-and-spoke intermediate representation for cross-provider LLM API translation and interoperability.
4/13/2026
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
BadSkill: backdoor attack formulation exploiting model artifacts bundled in agent skills.
4/13/2026
The AI Codebase Maturity Model: From Assisted Coding to Self-Sustaining Systems
AI Codebase Maturity Model framework for systematic progression from assisted coding to self-sustaining systems.
4/13/2026
On the Representational Limits of Quantum-Inspired 1024-D Document Embeddings: An Experimental Evaluation Framework
Experimental evaluation framework for quantum-inspired 1024-D document embeddings in RAG and information retrieval applications.
4/13/2026
Many-Tier Instruction Hierarchy in LLM Agents
Instruction Hierarchy in LLM Agents arXiv paper addressing multi-source conflicting instructions in LLM systems. Examines privilege levels for safe instruction following.
4/13/2026
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
ECHO arXiv paper on one-step diffusion model for chest X-ray report generation. Compresses multi-step denoising to single parallel generation step.
4/13/2026
SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
SafeAdapt arXiv paper on provably safe policy updates in deep RL for non-stationary environments. Addresses safety preservation during policy changes.
4/13/2026
XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers
Attack method demonstrating model poisoning vulnerabilities in federated learning without requiring collusion between adversarial clients.
4/13/2026
RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
Post-training approach enabling LLMs to effectively retrieve and use long-context information for improved reasoning capabilities.
4/13/2026
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
BERT-based evaluation method for LLM outputs that addresses limitations of rigid lexical evaluation and formatting-dependent scoring.
4/13/2026
VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
Agentic system for visual retrieval-augmented generation with iterative search and multi-step reasoning across visually rich documents.
4/13/2026
Semantic Rate-Distortion for Bounded Multi-Agent Communication: Capacity-Derived Semantic Spaces and the Communication Cost of Alignment
Theoretical framework showing how agents with different computational capacities can develop distinct semantic alphabets for communication.
4/13/2026
Envisioning the Future, One Step at a Time
Method for predicting future scene evolution by modeling uncertainty and simulating trajectories rather than dense pixel-level changes.
4/13/2026
VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
Technique for decoupled confidence calibration in large vision-language models to reduce hallucinations and improve reliability.
4/13/2026
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Approach using synthetic images to improve visual perception capabilities in vision-language models for spatial reasoning tasks.
4/13/2026
Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
Method for robust prompt learning in vision-language models that leverages visual content to handle label noise effectively.