15h ago
Transfer learning for nonparametric Bayesian networks
Transfer learning methods for nonparametric Bayesian networks under scarce data with constraint-based and score-based algorithms.
15h ago
Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars
Body model ablation replaces SMPL with Momentum Human Rig for 3D Gaussian avatar generation with simpler architecture.
15h ago
ProdCodeBench: A Production-Derived Benchmark for Evaluating AI Coding Agents
ProdCodeBench evaluates AI coding agents using production-derived tasks reflecting real developer-agent sessions and workflows.
15h ago
Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation
Visual attention inertia in MLLMs causes cognitive hallucinations; proposes mitigation for compositional understanding.
15h ago
Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling
Convolutional surrogate model for accelerating 3D discrete fracture-matrix simulations in groundwater flow modeling.
15h ago
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
LiME achieves expert specialization in multimodal MoE-PEFT via lightweight modulation instead of separate adapters per expert.
15h ago
SIEVE: Sample-Efficient Parametric Learning from Natural Language
SIEVE enables sample-efficient parametric learning from natural language instructions and feedback without high-quality traces.
15h ago
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
Model scheduling for masked diffusion language models uses smaller models at early denoising steps for faster generation.
15h ago
LLM Reasoning with Process Rewards for Outcome-Guided Steps
Process reward models improve LLM mathematical reasoning by providing step-level feedback on intermediate errors, not just final outcomes.
15h ago
Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
Fairness-aware GNN training using contrastive learning and counterfactual augmentation to mitigate biases from graph structure.
15h ago
Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
LLM-based compression using domain-adapted LoRA for lossless and lossy text compression achieving 2x improvements.
15h ago
Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
Systematic characterization of WebGPU dispatch overhead for LLM inference across GPU vendors, backends, and browsers at batch size 1.
15h ago
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
UI-Oceanus framework scales GUI agents via synthetic environmental dynamics and self-supervised learning instead of costly human demonstrations.
15h ago
DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery
Benchmark evaluating LLM and embedding performance for drug discovery tasks, assessing advantages over traditional methods.
15h ago
FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting
Frequency-aware Transformer for carbon footprint forecasting in power grids using periodic patterns and exogenous variables.
15h ago
Contextual Intelligence The Next Leap for Reinforcement Learning
Contextual RL improves agent generalization by exposing agents to environment characteristics for better zero-shot transfer beyond training distribution.
15h ago
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
OPRIDE method for offline preference-based RL reducing human feedback queries through efficient in-dataset exploration strategies.
15h ago
Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
Differentiable Symbolic Planning architecture combining neural networks with discrete symbolic reasoning for constraint satisfaction problems.
15h ago
Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
Framework for modeling and controlling ML model reliability under temporal distribution shift during deployment with continuous monitoring.
15h ago
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
Contrastive prompt tuning method to optimize LLMs for generating energy-efficient code aligned with Green Software Development goals.
15h ago
Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
PRISM framework for zero-shot policy transfer in RL using interpretable concept clustering with causal validation across different algorithms.
15h ago
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
Entropy-based analysis of combining Chain-of-Thought with RL for text-to-image generation, showing exploration-optimization tradeoffs.
15h ago
YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches
Live benchmark dataset for forecasting startup success using Y Combinator batches with three-month evaluation cycles.
15h ago
Dynamical structure of vanishing gradient and overfitting in multi-layer perceptrons
Dynamical systems analysis of vanishing gradient and overfitting in multi-layer perceptrons using minimal models.
15h ago
Self-Directed Task Identification
Self-Directed Task Identification framework enabling models to autonomously identify target variables in zero-shot settings without pretraining.
15h ago
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
Physics-informed deep generative models for offline RL in spaceflight to mitigate sim-to-real gap with limited real-world training data.
15h ago
Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD
Open-source benchmarking of Matrix Profile methods for time-series anomaly detection on univariate and multivariate datasets.
15h ago
Do We Need Frontier Models to Verify Mathematical Proofs?
Study comparing frontier vs smaller LLMs for mathematical proof verification, evaluating whether expensive models are necessary for proof checking.
15h ago
On the Geometric Structure of Layer Updates in Deep Language Models
Analysis of layer-to-layer representation changes in language models, decomposing updates into tokenwise and residual components.
15h ago
VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales
VALOR framework for B2B sales revenue uplift modeling handling zero-inflated distributions with treatment-gated representation learning.
15h ago
Time-Warping Recurrent Neural Networks for Transfer Learning
Transfer learning method for RNNs using time-warping rescaling, with theoretical analysis for linear differential equation models.
15h ago
SEDGE: Structural Extrapolated Data Generation
Framework for generating synthetic data under specified conditions with approximate identifiability guarantees for data distribution extrapolation.
15h ago
Causal-Audit: A Framework for Risk Assessment of Assumption Violations in Time-Series Causal Discovery
Framework for validating assumptions in time-series causal discovery through calibrated risk assessment and effect-size diagnostics.
15h ago
Re-analysis of the Human Transcription Factor Atlas Recovers TF-Specific Signatures from Pooled Single-Cell Screens with Missing Controls
Re-analysis of transcription factor atlas single-cell perturbation screen with improved quality control pipeline and MORF barcode demultiplexing.
15h ago
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
Low-precision training method for LLMs using adaptive Hadamard transforms based on outlier patterns in weights, activations, and gradients.
15h ago
Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits
Research on using LLM-generated synthetic data to warm-start contextual bandits, examining alignment between LLM choices and actual user preferences.
15h ago
A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction
Spectral framework for multi-scale nonlinear dimensionality reduction balancing global-local structure preservation and expressiveness-transparency.
15h ago
Fast NF4 Dequantization Kernels for Large Language Model Inference
Optimized NF4 dequantization kernels for fast LLM inference on NVIDIA GPUs, addressing FP16 conversion bottleneck.
15h ago
Communication-Efficient Distributed Learning with Differential Privacy
Communication-efficient distributed learning algorithm with differential privacy using local training and gradient clipping.
15h ago
ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models
ROMAN operator for time series that creates multiscale representations by building antialiased pyramids for convolutional classifiers.
15h ago
VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
VoxelCodeBench platform benchmarking code generation models for 3D spatial reasoning with execution in Unreal Engine.
15h ago
Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens
Analysis of function vectors in LLMs showing they steer behavior beyond logit lens interpretability across 4,032 cross-template transfer pairs.
15h ago
Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems
Complex-valued GNNs for distributed control of networked systems with basis-invariance for GPS and compass-denied environments.
15h ago
Analytic Drift Resister for Non-Exemplar Continual Graph Learning
Continual graph learning without storing exemplars, using class-level prototypes and analytic continual learning to address catastrophic forgetting.
15h ago
AXELRAM: Quantize Once, Never Dequantize
AXELRAM smart SRAM architecture computing attention scores from quantized KV cache without dequantization using orthogonal-transform quantization.
15h ago
Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
Distributed GNN training with communication-free sampling and 4D hybrid parallelism for scaling mini-batch learning on large graphs.
15h ago
Generalization Limits of Reinforcement Learning Alignment
Study of generalization limits in RLHF alignment, proposing compound jailbreaks targeting LLM safety through redistribution of existing capabilities.
15h ago
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
Theoretical analysis of gradient descent training at edge of stability with product-stability property for convergence guarantees.
15h ago
Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
Low-rank compression of pretrained models using randomized subspace iteration for efficient SVD-based model reduction.
15h ago
A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation
Physics-informed neural networks coupled with finite difference methods for thermal-hydraulic system simulation.