Entities · Labs
IArxiv
31 articles tagged with this entity.
-
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
-
x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability
-
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
-
Parameter-Free Encoders Remain Viable for RDB Foundation Models
-
Spectral Rewiring for Exploration, Purification, and Model Merging
-
Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters
-
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
-
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
-
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
-
Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?
-
CAREBench: A Child-Safety Risk Benchmark for Language Models
-
Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns
-
Towards Evaluating Data Priors for Tabular Foundation Models
-
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
-
Online Data Selection for Instruction Tuning via Gaussian Processes
-
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
-
Quantum Generative Diffusion Model for Real-World Time Series
-
Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
-
Spectral Retrieval-Augmented Time-Series Forecasting
-
MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
-
Deep Reinforcement Learning for Minimum Zero-Forcing Sets
-
DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels
-
Constitutional Value Potentials: reading and steering internal priority margins in language models
-
Topological Flow Matching
-
Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes
-
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
-
Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation
-
Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
-
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
-
GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting