5/6/2026
Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects
Survey of intelligent agents with emotional intelligence capabilities for human-computer interaction and affective computing systems.
5/6/2026
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
Balanced fine-tuning method for aligning LLMs with biomedical knowledge by addressing uncertainty structure differences in scientific text.
5/6/2026
2D-ThermAl: Physics-Informed Framework for Thermal Analysis of Circuits using Generative AI
Physics-informed generative AI framework for thermal circuit analysis, accelerating early-stage design validation vs traditional FEM simulation.
5/6/2026
jina-vlm: Small Multilingual Vision Language Model
2.4B parameter multilingual vision-language model achieving SOTA performance on multilingual VQA with token-efficient image processing.
5/6/2026
InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
Training-free algorithm for unbounded terrain generation using diffusion models, combining procedural noise efficiency with learned fidelity.
5/6/2026
A Neuro-Symbolic Framework for Accountability in Public-Sector AI
Neuro-symbolic explainability framework for public-sector AI systems, linking AI decisions to legal requirements using structured knowledge representation.
5/6/2026
How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
Cognitive-semantic analysis of prompt engineering as natural-language control mechanism, using frame activation and salience to explain LLM behavior modification.
5/6/2026
Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection
Framework for multimodal fake news detection using conflict-consensus approach that leverages cross-modal discrepancies instead of enforcing consistency.
5/6/2026
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
InstructMoLE: Parameter-efficient fine-tuning of Diffusion Transformers using Mixture of Low-rank Experts with instruction-guided routing for multi-conditional image generation.
5/6/2026
LVLM-Aided Alignment of Task-Specific Vision Models
Research using Large Vision-Language Models to align task-specific vision models with human domain knowledge, reducing spurious correlations.
5/6/2026
LinMU: Multimodal Understanding Made Linear
Using large vision-language models to improve alignment of task-specific vision models with human knowledge.
5/6/2026
OpenAI GPT-5 System Card
OpenAI GPT-5 system card describing unified architecture with fast base model, deeper reasoning model, and real-time router for task-appropriate model selection.
5/6/2026
From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level
RepoReason benchmark for evaluating agentic code reasoning at repository level with white-box diagnostics for logical consistency across interdependent file systems.
5/6/2026
False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
Study of emoticon semantic confusion vulnerability in LLMs where ASCII-based emoticons cause misinterpretation and unintended actions.
5/6/2026
STAGE: A Full-Screenplay Benchmark for Reasoning over Evolving Storie
STAGE benchmark for evaluating model reasoning over full-screenplay narratives, testing story comprehension, character tracking, and multi-form generation consistency.
5/6/2026
Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility
RoundTripCodeEval benchmark evaluating code-LLM reasoning consistency through forward-backward execution via lossless compression algorithm round-trip fidelity.
5/6/2026
Can professional translators identify machine-generated text?
Empirical study testing whether professional translators can identify AI-generated text from ChatGPT-4o versus human authors without specialized training.
5/6/2026
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
Method using vector alignment to resolve jailbreak-overrefusal trade-off in safety-aligned LLMs by separately encoding answer vectors and safety judgment vectors.
5/6/2026
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
Diagnostic study comparing iterative RAG with static RAG for multi-hop scientific question answering, analyzing when synchronized retrieval-reasoning loops provide benefits over single-pass approaches.
5/6/2026
Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
TCLA framework enables cross-session neural decoding with limited target data using task-conditioned latent alignment from source sessions.
5/6/2026
VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning
VERGE neurosymbolic framework combines LLMs with SMT solvers for verification-guided reasoning, decomposing outputs into formal logic for consistency checking.
5/6/2026
CoFrGeNet: Continued Fraction Architectures for Language Generation
CoFrGeNets introduces continued fraction-inspired architecture replacing attention and feed-forward layers in Transformers for improved language generation.
5/6/2026
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
GRACE framework unifies quantization-aware training and knowledge distillation for efficient vision-language models using information bottleneck principle.
5/6/2026
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
VideoGPA adds geometric priors to video diffusion models via self-supervised preference alignment to improve 3D structural consistency in generated videos.
5/6/2026
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
MCP-Atlas large-scale benchmark for evaluating LLM tool-use competency with 36 real Model Context Protocol servers, capturing real-world tool invocation complexity.
5/6/2026
STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
STEP warm-starts diffusion-based visuomotor policies with spatiotemporal consistency prediction to reduce inference latency for real-time robotic control.
5/6/2026
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
Control Reinforcement Learning trains policy to select sparse autoencoder features for interpretable token-level steering of LLMs, producing explainable intervention logs.
5/6/2026
From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
Comprehensive investigation of post-training pipeline for LLM-based vulnerability detection, demonstrating on-policy RL with GRPO outperforms supervised fine-tuning approaches.
5/6/2026
CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
CrispEdit scalable second-order algorithm for LLM editing that preserves general capabilities while making targeted behavior changes, treating capability preservation as explicit constraint.
5/6/2026
HistCAD: A Constraint-Aware Parametric History-Based CAD Representation, Dataset, and Benchmark with Industrial Complexity
HistCAD benchmark and dataset for parametric CAD generation with constraint preservation under edits, measuring design intent retention rather than just reconstruction fidelity.
5/6/2026
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
VAUQ proposes vision-aware uncertainty quantification for large vision-language models to reduce hallucinations and enable safe self-evaluation in vision-conditioned predictions.
5/6/2026
LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
LittleBit-2 achieves extreme LLM compression via sub-1-bit quantization using latent geometry alignment to maximize spectral energy gain in binary approximations.
5/6/2026
ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files
ContextCov derives executable constraints from LLM agent instruction files to enforce project-specific coding conventions, preventing constraint violations during autonomous software engineering tasks.
5/6/2026
Recurrent Graph Neural Networks and Arithmetic Circuits
Characterization of recurrent graph neural network computational power using arithmetic circuits framework, establishing theoretical bounds for GNN expressiveness.
5/6/2026
The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
Mechanistic interpretability study of grokking phenomenon in Transformers through architectural topology modifications to understand delayed generalization in modular arithmetic tasks.
5/6/2026
Grounding Synthetic Data Generation With Vision and Language Models
Vision-language grounded framework for interpretable synthetic data augmentation using VLMs to evaluate synthetic data quality through downstream task contribution rather than latent feature similarity.
5/6/2026
FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
FastDSAC framework scales maximum entropy reinforcement learning to high-dimensional humanoid control by addressing exploration inefficiency and training instability in policy gradient methods.
5/6/2026
Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms
Loss landscape visualization method for analyzing critic networks in actor-critic reinforcement learning algorithms.
5/6/2026
DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns
Deep reinforcement learning framework using graph neural networks for adaptive defense against multi-stage APT campaigns.
5/6/2026
Retrieval-Augmented LLMs for Security Incident Analysis
RAG-based system for automated cybersecurity incident analysis that queries multiple log sources to identify indicators and reconstruct attack events.
5/6/2026
PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning
Physics-informed contextual spectral reinforcement learning for adaptive sensing in high-dimensional low-sample-size environments.
5/6/2026
GISclaw: A Comprehensive Open-Source LLM Agent System for Realistic Multi-Step Geospatial Analysis
Open-source LLM agent system for multi-step geospatial analysis workflows including spatial joins, kriging, and machine-learning classification.
5/6/2026
Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding
Fine-tuned CLIP model improving vision-language model understanding of presence-based and absence-based negation expressions.
5/6/2026
Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era
Framework for accessible XAI targeting blind and low-vision users, addressing explainability gaps in autonomous AI agent systems.
5/6/2026
Gradient Boosting within a Single Attention Layer
Gradient-boosted attention mechanism within transformer layers applying boosting principles for error correction in a single attention layer.
5/6/2026
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
Privacy-preserving LLM-based system for analyzing classroom videos to assess student attention without storing identifiable footage.
5/6/2026
Delayed homomorphic reinforcement learning for environments with delayed feedback
Reinforcement learning algorithm for delayed-feedback environments using homomorphic approach to avoid state-space explosion.
5/6/2026
How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
Empirical study of how reasoning develops in LLMs from SFT to RL using chess, finding unfaithful reasoning patterns during RL stage.
5/6/2026
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
Study of social dynamics vulnerabilities in multi-agent LLM collectives, analyzing conformity, expertise perception, and speaker dominance effects.
5/6/2026
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Master Key Hypothesis proposing capability transfer across models via linear subspace alignment without retraining; introduces UNLOCK method.