3/17/2026
Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Systematic study of post-training quantization methods for diffusion LLMs to enable edge device deployment, comparing compression techniques.
3/17/2026
Learning to Generate Unit Test via Adversarial Reinforcement Learning
UTRL: reinforcement learning framework training LLMs to generate high-quality unit tests automatically, addressing test generation challenges.
3/17/2026
The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
Research evaluating Law-Following AI framework for embedding legal compliance in advanced AI agents, analyzing legal personhood constructs and technical feasibility.
3/17/2026
Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking
Trajectory-based paradigm for efficient 3D point cloud tracking in robotics and autonomous systems.
3/17/2026
OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
Reinforcement learning approach for radiology report generation using FactScore-based rewards with reduced data requirements.
3/17/2026
Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations
Framework evaluating robustness of Vision-Language-Action models under real-world physical variations for robotic tasks.
3/17/2026
SloPal: A 60-Million-Word Slovak Parliamentary Corpus with Aligned Speech and Fine-Tuned ASR Models
Slovak parliamentary speech corpus with 66M words and fine-tuned ASR models for low-resource language recognition.
3/17/2026
Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling
Data-efficient ASR personalization using phoneme-level uncertainty scoring and variational inference. Guides fine-tuning for non-normative speech recognition.
3/17/2026
Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Variational low-rank adaptation method for personalizing speech recognition on impaired speech using foundation models. Addresses acoustic variability and data scarcity.
3/17/2026
Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving
Autoregressive method for autonomous driving combining HD map construction with persistent traffic rule awareness across extended driving sequences.
3/17/2026
Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning
Matched-compute study evaluating synthetic data interventions for in-context learning in language models. Tests mechanism-targeted pretraining effects.
3/17/2026
Reducing Cost of LLM Agents with Trajectory Reduction
Method for reducing LLM agent inference costs through trajectory reduction. Addresses token cost efficiency in multi-turn agent systems for software engineering.
3/17/2026
Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State
Continuous-time reinforcement learning theory with deterministic policy gradients for continuous state and action spaces.
3/17/2026
XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
Deep reinforcement learning optimization method using eigenspectrum analysis and condition numbers to improve sample efficiency and critic network performance.
3/17/2026
Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
Technique reducing LLM reasoning model overthinking through decoupled rewards and curriculum scheduling. Addresses excessive token generation without performance gain.
3/17/2026
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
Variational flow matching approach for vector-quantized image generation combining categorical supervision with continuous transport dynamics.
3/17/2026
Diverse Text-to-Image Generation via Contrastive Noise Optimization
Diffusion model method for diverse text-to-image generation via contrastive noise optimization. Addresses mode collapse in text-guided image synthesis.
3/17/2026
Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
Reinforcement learning framework (SFPO) for improving LLM reasoning by decomposing policy optimization into slow and fast components to reduce training instability.
3/17/2026
Emergent Coordination in Multi-Agent Language Models
Information-theoretic framework measuring higher-order structure and emergence in multi-agent LLM systems. Tests for dynamical emergence in agent coordination.
3/17/2026
Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models
Model-native technique to explain LLM hallucinations using layer-wise semantic maps. Traces concept flow through residual streams via unembedding.
3/17/2026
Dynamic Stress Detection: A Study of Temporal Progression Modelling of Stress in Speech
Method for detecting psychological stress from speech using temporal modeling with cross-attention. Treats stress as dynamically evolving phenomenon.
3/17/2026
Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition
Comprehensive overview of Ultralytics YOLO object detection model evolution from YOLOv5 to YOLO26. Details architectural improvements and benchmarking.
3/17/2026
Qubit-centric Transformer for Surface Code Decoding
Transformer-based neural network decoder for quantum error correction. Applies deep learning to quantum computing reliability.
3/17/2026
A Functional Perspective on Knowledge Distillation in Neural Networks
Theoretical analysis of knowledge distillation in neural networks from a functional perspective. Decouples compression from architecture reduction.
3/17/2026
DiffOPF: Diffusion Solver for Optimal Power Flow
Deep learning approach using diffusion models to solve optimal power flow problems in electrical grids. Captures multi-valued solution mappings.
3/17/2026
SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
Benchmark and methods for editing knowledge in audio-language models without retraining. First work on auditory attribute knowledge editing.
3/17/2026
CARE: Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams
Machine learning method for recognizing daily activities from sensor data using contrastive learning. Addresses ambient assisted living applications.
3/17/2026
Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
Justitia scheduling algorithm for fair and efficient execution of task-parallel LLM agents on shared GPUs. Resource scheduling optimization for agent systems.
3/17/2026
StreamingTOM: Streaming Token Compression for Efficient Video Understanding
StreamingTOM training-free token compression for streaming video understanding. Efficiency optimization for video vision-language models.
3/17/2026
GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
GlobalRAG reinforcement learning approach for multi-hop question answering with improved global reasoning. RAG system enhancement via RL for better query planning.
3/17/2026
Eyes on Target: Gaze-Aware Object Detection in Egocentric Video
Gaze-guided object detection framework for egocentric videos using vision transformers. Computer vision with attention mechanisms.
3/17/2026
Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
Annotation scheme for collaborative dialogue corpus capturing speaker perspectives in misunderstandings. Linguistics and NLP dataset annotation work.
3/17/2026
VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models
Zero-shot robotic grasp detection using vision-language models without training data or retraining. Robotics application leveraging VLMs.
3/17/2026
IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction
Semi-supervised intent detection framework with active learning correction for voice dialog agents. LLM application for dialog system improvement.
3/17/2026
GazeVLM: A Vision-Language Model for Multi-Task Gaze Understanding
Vision-language model for unified gaze understanding combining detection, target, and object recognition. Multimodal model for attention estimation.
3/17/2026
More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists
Study of multi-agent LLM cooperation on math problems with analysis of adversarial robustness. Evaluates agent collaboration and vulnerability to perturbations.
3/17/2026
Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization
Privacy-preserving explainable AI for IoT applications using SHAP entropy regularization. Focuses on interpretability and privacy in edge devices.
3/17/2026
PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs
Training-free stabilizer (PAS) fixing temporal inconsistency in video LLMs caused by rotary position embedding ripples. Technical improvement for video understanding.
3/17/2026
Decoupled Action Expert: Confining Task Knowledge to the Conditioning Pathway
Decoupled action expert for vision-language-action models using diffusion/flow-matching for manipulation policies. Computer vision and robotics research.
3/17/2026
Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
Physical adversarial attack against stereo depth estimation in autonomous driving perception. Security research without direct relevance to stated interests.
3/17/2026
Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
Fast inference acceleration for masked auto-regressive diffusion models enabling practical reinforcement learning. Optimization technique for generative models in RL contexts.
3/17/2026
Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation
Pipeline for speaker-attributed civic simulation using LLMs from ASR transcripts. LLM application for multi-agent deliberation modeling.
3/17/2026
Explainable Visual Anomaly Detection via Concept Bottleneck Models
Concept bottleneck models for explainable visual anomaly detection with semantic interpretability. Computer vision research with interpretability focus.
3/17/2026
MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
MapReduce LoRA and RaTE methods for multi-preference optimization in generative models using RLHF. Advances alignment of LLMs through parameter-efficient fine-tuning techniques.
3/17/2026
TimesNet-Gen: Deep Learning-based Site Specific Strong Motion Generation
Deep learning model for generating site-specific earthquake ground motion from accelerometer records. Domain-specific application without relevance to stated interests.
3/17/2026
Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
Review of uncertainty quantification and data efficiency methods for AI systems in robotics, telecommunications, and healthcare. Theoretical ML research with practical applications.
3/17/2026
Composing Concepts from Images and Videos via Concept-prompt Binding
Method for composing visual concepts from images and videos using prompt token binding. Computer vision research without clear AI agent or LLM application focus.
3/17/2026
LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification
Combines large language models with transformer encoders for financial news classification with limited labeled training data.
3/17/2026
Rough Sets for Explainability of Spectral Graph Clustering
Rough set theory applied to explain results of spectral graph clustering algorithms for text document analysis.
3/17/2026
Dynamical Mechanisms for Coordinating Long-term Working Memory Based on the Precision of Spike-timing in Cortical Neurons
Neuroscience study of cortical neuron mechanisms underlying long-term working memory through spike-timing precision analysis.