3/25/2026
EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
Video world models for robotics using inverse dynamics rewards to align generated trajectories with executable robot actions.
3/25/2026
Elastic Weight Consolidation Done Right for Continual Learning
Systematic analysis of Elastic Weight Consolidation for continual learning showing suboptimal performance and proposing improvements to weight importance estimation.
3/25/2026
myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition
Benchmark comparing PETNN, KAN, and classical deep learning models on Burmese handwritten digit recognition dataset.
3/25/2026
Mi:dm K 2.5 Pro
Mi:dm K 2.5 Pro, 32B parameter enterprise LLM supporting multi-step reasoning, long-context understanding, and agentic workflows in Korean and domain-specific applications.
3/25/2026
Agent Control Protocol: Admission Control for Agent Actions
Formal specification for admission control governance of autonomous agents in institutional B2B environments with cryptographic validation.
3/25/2026
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
Graph-based memory system for LLM reward prediction requiring limited labeled data for reinforcement learning post-training.
3/25/2026
Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation
Research on chain-of-thought faithfulness in LLMs showing measurement methodology significantly affects reported faithfulness scores across 12 open-weight models.
3/25/2026
Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
KidGym: 2D grid-based reasoning benchmark evaluating MLLMs on spatial intelligence inspired by Wechsler Intelligence Scales.
3/25/2026
CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language
CRoCoDiL: Continuous semantic space diffusion model for non-autoregressive language generation with improved coherence.
3/25/2026
An Industrial-Scale Retrieval-Augmented Generation Framework for Requirements Engineering: Empirical Evaluation with Automotive Manufacturing Data
Industrial-scale RAG framework evaluated on automotive manufacturing requirements engineering with unstructured heterogeneous documentation.
3/25/2026
MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
Memory-Keyed Attention: Efficient attention mechanism reducing KV cache memory for long-context LLM inference and training.
3/25/2026
TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological
TRACE: Multi-agent system using autonomous reasoning for seismological analysis of earthquake mechanisms from geophysical observations.
3/25/2026
When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning
Unsupervised self-evolution training framework for multimodal LLMs achieving reasoning improvements without annotated data.
3/25/2026
DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns
DeepXplain: Explainable deep reinforcement learning framework for multi-stage APT cyber defense with provenance graphs.
3/25/2026
LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
Case study on LLM-powered workflow optimization for multidisciplinary software development in automotive industry.
3/25/2026
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
mSFT: Iterative algorithm addressing overfitting in multi-task supervised fine-tuning by heterogeneous data mixture optimization.
3/25/2026
Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
arXiv paper on safe offline reinforcement learning with budget constraints. Addresses safety-reward trade-offs in sequential decision making.
3/25/2026
Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
Research on synthetic data generation using LLMs to improve smaller model fine-tuning. Analyzes diversity and distribution in embedding space.
3/25/2026
Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
Uncertainty estimation method for LLMs using intra-layer local information scores from cross-layer agreement patterns.
3/25/2026
Scaling Attention via Feature Sparsity
Sparse Feature Attention method reducing transformer self-attention complexity through feature-level sparsity instead of sequence-level sparsity.
3/25/2026
Latent Semantic Manifolds in Large Language Models
Mathematical framework interpreting LLM hidden states as points on latent semantic manifolds with Riemannian geometry.
3/25/2026
Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
Training-free hallucination detector for LLMs using sample transform cost to measure output distribution complexity.
3/25/2026
Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization
Progressive Quantization method for robust vector tokenization in multimodal LLMs and diffusion models.
3/25/2026
CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News
Chinese financial news dataset and benchmark for evaluating LLMs as autonomous agents in macro and sector asset allocation.
3/25/2026
UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
UniFluids: conditional flow-matching framework using diffusion Transformers to unify learning solution operators across diverse PDEs.
3/25/2026
Emergency Preemption Without Online Exploration: A Decision Transformer Approach
Decision Transformer approach for offline emergency vehicle signal preemption optimization without online exploration.
3/25/2026
DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
Delta-Aware Quantization framework for post-training LLM weight compression that preserves knowledge by protecting small-magnitude parameter deltas during quantization.
3/25/2026
A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance
Classification method for wind power ramp event forecasting addressing severe class imbalance in grid stability systems.
3/25/2026
Trained Persistent Memory for Frozen Decoder-Only LLMs
Method for adding trained persistent memory to frozen decoder-only LLMs using memory adapters in latent space.
3/25/2026
Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models
Distribution-free safety guarantees for wildfire evacuation mapping using conformal prediction with tabular, spatial, and graph models.
3/25/2026
Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms
Comparative study of LLMs for missing data imputation with analysis of hallucination effects and control mechanisms.
3/25/2026
Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
State-space model enhancement combining graph signal processing with Mamba2 for efficient language modeling.
3/25/2026
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
Analysis of systematic biases in Chinchilla scaling law fitting method with implications for compute-optimal LLM allocation.
3/25/2026
Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
Cloud-edge collaborative framework using large models for robust photovoltaic power forecasting with latency constraints.
3/25/2026
First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution
Research on first-mover bias in gradient boosting feature importance explanations under multicollinearity conditions.
3/25/2026
COMPASS-Hedge: Learning Safely Without Knowing the World
Online learning algorithm balancing regret guarantees in adversarial and stochastic settings with safety constraints.
3/25/2026
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
Web-grounded iterative self-play framework for improving LLM reasoning through reinforcement learning with verifiable rewards.
3/25/2026
Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
Neural tangent kernel framework for understanding continuous representation full-waveform inversion in geophysical applications.
3/25/2026
MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives
Research establishing equivalence between classifier-free guidance and alignment objectives in diffusion model training.
3/25/2026
FAAR: Format-Aware Adaptive Rounding for NVFP4
Format-aware quantization method for deploying LLMs on edge devices using NVFP4 ultra-low bit precision.
3/25/2026
Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
Research on multimodal fusion strategies for time series forecasting using text and vision modalities with constrained approaches.
3/25/2026
Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
Study evaluating whether LoRA adapters trained with instruction-tuning objectives actually improve instruction-following capability across different tasks using IFEval benchmarks.
3/25/2026
Symbolic Graph Networks for Robust PDE Discovery from Noisy Sparse Data
Symbolic Graph Networks framework for discovering PDEs from noisy, sparse observational data using machine learning instead of numerical differentiation.
3/25/2026
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
Reinforcement learning approach for learning optimal decision timing in continuous environments using predictive temporal signals.
3/25/2026
Neural Structure Embedding for Symbolic Regression via Continuous Structure Search and Coefficient Optimization
Symbolic regression framework using continuous structure search and neural embeddings for interpretable equation discovery.
3/25/2026
Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning
Offline reinforcement learning with model predictive control using differentiable world models for inference adaptation.
3/25/2026
SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
Skill retrieval and ranking system for LLM agents selecting relevant tools from thousands of overlapping options at scale.
3/25/2026
A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning
Energy-aware gradient pruning framework for federated learning accounting for hardware transmission costs.
3/25/2026
Multimodal Training to Unimodal Deployment: Leveraging Unstructured Data During Training to Optimize Structured Data Only Deployment
Multimodal training framework leveraging unstructured clinical notes to improve structured EHR data deployment.
3/25/2026
A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
Foundation model for time-series in-context learning using quantile-regression T5 with instruction conditioning.