4/20/2026
Constant-Factor Approximations for Doubly Constrained Fair k-Center, k-Median and k-Means
arXiv paper on constant-factor approximation algorithms for fair k-clustering with demographic constraints.
4/20/2026
Towards Universal Convergence of Backward Error in Linear System Solvers
arXiv paper on backward error analysis and convergence for linear system solvers in numerical linear algebra.
4/20/2026
Early Detection of Acute Myeloid Leukemia (AML) Using YOLOv12 Deep Learning Model
arXiv paper applying YOLOv12 deep learning model for multiclass acute myeloid leukemia cell classification.
4/20/2026
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance
arXiv paper on ST-STORM self-supervised learning approach for appearance-based image representation.
4/20/2026
Sentiment Analysis of German Sign Language Fairy Tales
arXiv paper on sentiment analysis dataset and LLM-based model for German sign language fairy tales.
4/20/2026
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency
arXiv paper on AtManRL method using differentiable attention for faithful chain-of-thought reasoning in LLMs.
4/20/2026
Adaptive multi-fidelity optimization with fast learning rates
arXiv paper on adaptive multi-fidelity optimization with cost-bias tradeoffs and learning rate analysis.
4/20/2026
Information Router for Mitigating Modality Dominance in Vision-Language Models
arXiv paper on Information Router to mitigate modality dominance in vision-language models.
4/20/2026
Learning to Reason with Insight for Informal Theorem Proving
arXiv paper proposing framework for informal theorem proving with LLMs using insight-driven reasoning.
4/20/2026
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
arXiv paper on ACSESS method for automatic combination of sample selection strategies in few-shot LLM learning.
4/20/2026
Heterogeneous Sheaf Neural Networks
arXiv paper proposing HetSheaf, a framework for heterogeneous graph neural networks across different node/edge types.
4/20/2026
Transformer Neural Processes - Kernel Regression
arXiv paper on HetSheaf framework for heterogeneous graph neural networks supporting multiple node/edge types in real-world applications.
4/20/2026
FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users
arXiv paper introducing Transformer Neural Processes addressing O(n²) attention bottleneck in Neural Processes with kernel regression.
4/20/2026
AutoNFS: Automatic Neural Feature Selection
arXiv paper on Few-Shot Preference Optimization (FSPO) for personalizing LLMs using meta-learning on synthetic preference data.
4/20/2026
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
arXiv paper on AutoNFS, automatic neural feature selection for high-dimensional tabular data with interpretability and efficiency focus.
4/20/2026
Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba
arXiv paper on Federated Prototype Learning combining textual semantics with visual representations to handle heterogeneous federated learning.
4/20/2026
An Information-Geometric Approach to Artificial Curiosity
Information-geometric framework for artificial curiosity in sparse-reward RL using intrinsic rewards invariant to representation.
4/20/2026
A Tale of Two Learning Algorithms: Multiple Stream Random Walk and Asynchronous Gossip
Theoretical and empirical analysis of decentralized learning algorithms comparing multi-stream random walk and asynchronous gossip approaches.
4/20/2026
Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification
Histogram-based parameter-efficient tuning (HPT) technique for transfer learning capturing target domain statistics in sonar classification.
4/20/2026
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Softpick: Rectified softmax replacement for transformer attention eliminating attention sink and reducing activations with improved quantization.
4/20/2026
ChemAmp: Amplified Chemistry Tools via Composable Agents
ChemAmp: Framework for composable LLM agents in chemistry using tool amplification to enhance multi-tool orchestration capabilities.
4/20/2026
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Token significance-aware RL method for LLM reasoning that optimizes token-level contributions rather than uniform length penalties.
4/20/2026
PyLO: Towards Accessible Learned Optimizers in PyTorch
PyLO: PyTorch package making learned optimizers accessible, providing drop-in replacements for standard optimizers like Adam.
4/20/2026
HiPreNets: High-Precision Neural Networks through Progressive Training
HiPreNets: Progressive training approach for neural networks achieving high precision in L-infinity norm error for safety-critical applications.
4/20/2026
Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation
Analysis of exploration-exploitation bias in offline evaluation of linear bandit recommender systems using contextual bandits.
4/20/2026
Self-Aligned Reward: Towards Effective and Efficient Reasoners
Self-aligned reward (SAR) method for LLM reasoning that provides fine-grained guidance beyond binary correctness to improve efficiency and accuracy.
4/20/2026
Online Distributionally Robust LLM Alignment via Regression to Relative Reward
Distributionally robust optimization approach for RLHF alignment addressing overoptimization in LLM training via relative reward regression.
4/20/2026
Bridging the phenotype-target gap for molecular generation via multi-objective reinforcement learning
SmilesGEN: VAE-based generative model using multi-objective RL for de novo drug molecule generation considering phenotypic effects.
4/20/2026
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
Empirical study of scaling behaviors in RL post-training for LLMs across Qwen2.5 models (0.5B-72B) focused on mathematical reasoning performance.
4/20/2026
Truncated Kernel Stochastic Gradient Descent with General Losses and Spherical Radial Basis Functions
Novel kernel SGD algorithm using spherical radial basis functions and regularization strategy for large-scale supervised learning with general losses.
4/20/2026
COMPASS: Benchmarking Constrained Optimization in LLM Agents
COMPASS benchmark evaluating LLM agents' ability to perform constrained optimization in multi-turn conversations for travel planning and scheduling tasks.
4/20/2026
Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
Study on entropy regularization with adaptive coefficients to improve LLM reasoning in reinforcement learning with verifiable rewards, addressing policy collapse.
4/20/2026
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
Research on optimal hyperparameters (clipping bound and batch size) for differentially private transfer learning, addressing theory-practice gaps.
4/20/2026
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
Systematic study demonstrating that enhancing LLM reasoning capabilities paradoxically increases tool hallucination in agent deployment scenarios.
4/20/2026
In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs
Training-free in-context distillation with self-consistency cascades to reduce LLM agent inference costs while maintaining quality and iteration speed.
4/20/2026
Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation
Approach using LLMs as lossless encoders/decoders for invertible problems like logic table to HDL conversion, mitigating hallucinations and omissions.
4/20/2026
Teaching Language Models Mechanistic Explainability Through MechSMILES
Framework teaching LLMs to predict chemical reaction mechanisms using arrow-pushing formalism notation for computer-assisted synthesis planning.
4/20/2026
Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
CadLLM training-free acceleration method for diffusion-based LLM inference using confidence-aware adaptive control of generation parameters.
4/20/2026
Information-Consistent Language Model Recommendations through Group Relative Policy Optimization
Group Relative Policy Optimization method for improving consistency and reliability of LLM recommendations across semantically equivalent prompts.
4/20/2026
Dynamic Tool Dependency Retrieval for Lightweight Function Calling
Dynamic tool dependency retrieval method for LLM-based function calling agents, improving tool selection and reducing context length for on-device agents.
4/20/2026
AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt
Federated learning approach for traffic prediction using adaptive prompts, enabling privacy-preserving collaborative training across distributed data.
4/20/2026
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
CoMeT architecture enabling LLMs to process arbitrarily long sequences with constant memory and linear time complexity via efficient plug-in module.
4/20/2026
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy using simulation-to-reality transfer learning.
4/20/2026
Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
Empirical analysis of adversarial attacks on safety-aligned LLMs showing polynomial-to-exponential growth in attack success rates with prompt injection.
4/20/2026
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
Proves attention sinks are functionally necessary in softmax transformers for certain tasks, formalizing their role beyond optimization artifacts.
4/20/2026
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
Continual learning framework for Fourier Neural Operators enabling model adaptation to new data distributions without retraining on prior data.
4/20/2026
Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario
Dynamical analysis of MLP training through saddle structures, explaining vanishing gradients and overfitting phenomena.
4/20/2026
Olmo Hybrid: From Theory to Practice and Back
Hybrid language models mixing RNNs and attention mechanisms, comparing performance advantages over pure transformers with theoretical and practical evidence.
4/20/2026
Neural Computers
Proposes Neural Computers that unify computation, memory, and I/O in learned runtime states, exploring general-purpose neural machine architectures.
4/20/2026
Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis
Leave-one-out analysis for evaluating SVG generation beyond visual similarity, assessing structural editability and reusability.