3/24/2026
TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols
TimeTox: LLM-based pipeline using Gemini for automated time toxicity extraction from clinical trial protocols.
3/24/2026
Generalized Discrete Diffusion from Snapshots
Generalized Discrete Diffusion from Snapshots framework supporting arbitrary noising processes over discrete state spaces.
3/24/2026
Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
Comprehensive efficiency comparison of 16 language models across NLP tasks with novel Performance-Efficiency Ratio metric.
3/24/2026
Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures
Analysis of instruction-tuned LLM failure modes showing error detection gaps across architectures.
3/24/2026
Efficient Fine-Tuning Methods for Portuguese Question Answering: A Comparative Study of PEFT on BERTimbau and Exploratory Evaluation of Generative LLMs
Comparative study of PEFT and quantization techniques for fine-tuning BERTimbau on Portuguese QA tasks.
3/24/2026
DRTriton: Large-Scale Synthetic Data Reinforcement Learning for Triton Kernel Generation
DRTriton: Synthetic data reinforcement learning pipeline for automatic CUDA kernel generation from PyTorch.
3/24/2026
CataractSAM-2: A Domain-Adapted Model for Anterior Segment Surgery Segmentation and Scalable Ground-Truth Annotation
CataractSAM-2: Domain-adapted Segment Anything Model 2 for surgical video segmentation and automated annotation.
3/24/2026
PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection
PRISM: Photonic accelerator design achieving O(1) memory access for long-context LLM inference via block selection.
3/24/2026
FedCVU: Federated Learning for Cross-View Video Understanding
Federated learning framework for privacy-preserving multi-camera video understanding across heterogeneous viewpoints.
3/24/2026
A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures
Comparative study of memorization mechanisms across multiple LLM model series including Pythia and OpenLLaMa.
3/24/2026
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
Memory-efficient zeroth-order optimization method with adaptive curvature guidance for fine-tuning large language models.
3/24/2026
Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
Framework for model selection and evaluation of hybrid quantum-classical transformer architectures.
3/24/2026
Ctrl-A: Control-Driven Online Data Augmentation
Automated data augmentation algorithm using control theory principles for dynamic adjustment during image model training.
3/24/2026
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Adaptive approach for selecting LoRA ranks per layer in diffusion model fine-tuning for personalized image generation.
3/24/2026
SecureBreak -- A dataset towards safe and secure models
Dataset and methods for improving security alignment and robustness of large language models against adversarial attacks.
3/24/2026
RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning
RAFL learns residual acceleration fields to reduce sim-to-real gap in soft robot control with differentiable simulators.
3/24/2026
MAGPI: Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data
MAGPI augments Gaussian processes with multifidelity data to improve surrogate modeling accuracy from limited high-fidelity observations.
3/24/2026
AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference
AnimalCLAP combines taxonomy-aware training with language-audio pretraining for species recognition and trait inference from vocalizations.
3/24/2026
SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
SpecTM applies physics-informed spectral masking to Earth observation foundation models for trustworthy band reconstruction in remote sensing.
3/24/2026
Data Curation for Machine Learning Interatomic Potentials by Determinantal Point Processes
Uses determinantal point processes for efficient data curation to select informative atomic configurations for ML interatomic potential training.
3/24/2026
Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models
Evaluates reliability and fidelity of using LLMs as judges for automated assessment of victim ML model outputs and quality.
3/24/2026
Gumbel Distillation for Parallel Text Generation
Gumbel Distillation enables parallel decoders to match autoregressive LLM quality by learning joint token distributions via novel distillation.
3/24/2026
One Model, Two Markets: Bid-Aware Generative Recommendation
GEM-Rec unifies semantic and commercial retrieval in generative recommender systems by incorporating bid-awareness for monetization.
3/24/2026
The Dual Mechanisms of Spatial Reasoning in Vision-Language Models
Analyzes two concurrent mechanisms in VLMs for spatial reasoning: content-independent spatial tokens and language-based spatial relations.
3/24/2026
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
ThinkJEPA combines V-JEPA latent world models with vision-language models for improved long-horizon semantic reasoning in video prediction.
3/24/2026
End-to-End Training for Unified Tokenization and Latent Denoising
UNITE enables end-to-end training of latent diffusion models with unified tokenization without separate staging phases.
3/24/2026
WorldCache: Content-Aware Caching for Accelerated Video World Models
WorldCache accelerates video diffusion Transformers via physics-aware feature caching across denoising steps with content-aware strategies.
3/24/2026
Relative Error Embeddings for the Gaussian Kernel Distance
Analyzes approximation quality of random Fourier features for Gaussian kernel RKHS embeddings with relative error bounds.
3/24/2026
Policy Optimization over General State and Action Spaces
Generalizes policy mirror descent for RL over continuous/general state and action spaces with convergence guarantees.
3/24/2026
Better Generative Replay for Continual Federated Learning
Introduces continual federated learning with generative replay for incremental task learning across distributed clients without storing history data.
3/24/2026
Geometric Imbalance in Semi-Supervised Node Classification
Theoretical analysis of geometric imbalance problem in semi-supervised graph node classification on imbalanced datasets.
3/24/2026
Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption
FHE-compatible neural architectures using modified Transformers and RNNs for privacy-preserving ML with reduced computational complexity.
3/24/2026
Revisit, Extend, and Enhance Hessian-Free Influence Functions
Extends Hessian-free influence functions for deep models, enabling sample importance assessment for interpretation and noisy label detection.
3/24/2026
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Reveals absorbing discrete diffusion models implicitly model conditional distributions via concrete score functions for language modeling.
3/24/2026
RoboMorph: Evolving Robot Morphology using Large Language Models
Automated modular robot design generation using LLMs and evolutionary algorithms with grammar-based representation and RL refinement.
3/24/2026
Strongly-polynomial time and validation analysis of policy gradient methods
Policy gradient methods with novel advantage gap termination criterion achieving strongly-polynomial convergence independent of optimal policy distribution.
3/24/2026
Meta-Transfer Learning Powered Temporal Graph Networks for Cross-City Real Estate Appraisal
Meta-transfer learning with temporal graph networks for real estate valuation across cities with limited data.
3/24/2026
Learning Hidden Physics and System Parameters with Deep Operator Networks
Deep operator networks for discovering hidden physics laws and system parameters from sparse observations without retraining.
3/24/2026
Effectiveness of Distributed Gradient Descent with Local Steps for Overparameterized Models
Analyzes Local-SGD/FedAvg convergence for overparameterized models in distributed training with local update steps.
3/24/2026
The Cost of Replicability in Active Learning
Investigates sample complexity cost of achieving replicable active learning algorithms across independent runs.
3/24/2026
Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network
Probabilistic neural network with incremental learning and unlearning capabilities using automatic construction without hyperparameter tuning.
3/24/2026
C-HDNet: Hyperdimensional Computing for Causal Effect Estimation from Observational Data Under Network Interference
Hyperdimensional computing approach for causal effect estimation from observational data with network confounding and interference.
3/24/2026
RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
Simplifies RLHF for LLM alignment by reformulating as supervised learning, reducing complexity and computational cost of PPO/GRPO methods.
3/24/2026
TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
Multi-modal time series prediction framework combining prototype encoders with three LLMs for improved accuracy and explainability.
3/24/2026
Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes
Applies reinforcement learning to insurance loss reserving under macroeconomic constraints using CVaR and PPO optimization.
3/24/2026
AlphaZero-Edu: Democratizing Access to AlphaZero
Educational implementation of AlphaZero reinforcement learning framework addressing complexity and reproducibility challenges for broader accessibility.
3/24/2026
An evolutionary perspective on modes of learning in Transformers
Analyzes Transformers through evolutionary biology lens, examining in-weight learning vs in-context learning as complementary inference strategies.
3/24/2026
Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning
Compares uniform loss vs specialized optimizers in multi-task learning, examining whether equal weighting can match task-specific optimization with proper hyperparameters.
3/24/2026
SSR: Speculative Parallel Scaling Reasoning in Test-time
SSR: Training-free framework for parallel decoding in LLMs, improving efficiency of test-time scaling reasoning.
3/24/2026
Learning to Reason without External Rewards
Intuitor: LLM reasoning method using internal confidence signals for RL without external rewards or labeled data.