3d ago
Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies
Symbolic-Neural Consistency Audit (SNCA) framework that extracts LLM self-stated safety policies via prompts and verifies model adherence to them.
3d ago
Beyond Segmentation: Structurally Informed Facade Parsing from Imperfect Images
YOLOv8-based facade parsing system augmented with alignment loss to enforce structural coherence in architectural element detection.
3d ago
Natural Riemannian gradient for learning functional tensor networks
Riemannian gradient descent approach for optimizing low-rank functional tensor networks on arbitrary loss functions beyond least-squares regression.
3d ago
Online Intention Prediction via Control-Informed Learning
Online intention prediction framework for autonomous systems using inverse reinforcement learning with time-varying objectives and unknown parameters.
3d ago
Iterative Identification Closure: Amplifying Causal Identifiability in Linear SEMs
Iterative Identification Closure framework for determining causal identifiability in linear structural equation models with latent confounders.
3d ago
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
Fragment-based graph neural network integrated with many-body expansion theory for predicting potential energy surfaces in chemical systems.
3d ago
Biologically-Grounded Multi-Encoder Architectures as Developability Oracles for Antibody Design
CrossAbSense framework using protein language model encoders and attention decoders to predict antibody properties for therapeutic design validation.
3d ago
Variational Quantum Physics-Informed Neural Networks for Hydrological PDE-Constrained Learning with Inherent Uncertainty Quantification
Hybrid quantum-classical physics-informed neural networks for hydrological modeling with uncertainty quantification using variational quantum circuits.
3d ago
Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
Theoretical analysis of loss landscape in two-layer ReLU neural networks, characterizing local minima and their connection to stochastic gradient descent dynamics.
3d ago
Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
Learning-to-Defer framework that routes inputs to experts while selecting additional information (retrieved documents, tool outputs) to provide each expert, extending traditional routing systems.
3d ago
PhysInOne: Visual Physics Learning and Reasoning in One Suite
Large-scale synthetic dataset with 2M videos covering physical phenomena for training physics-aware AI systems.
3d ago
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM
Systematic comparison of LLM task adaptation strategies including instruction revision, prompt optimization, and retrieval methods.
3d ago
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
Video diffusion model learning joint distribution of video frames and camera trajectories for novel view synthesis.
3d ago
Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet
Neural network architecture for haptic signal prediction in tactile internet using mode decomposition.
3d ago
An Open-Source, Open Data Approach to Activity Classification from Triaxial Accelerometry in an Ambulatory Setting
Open-source dataset and code for classifying human activity from accelerometer sensor data.
3d ago
XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers
Model poisoning attack on federated learning without client collusion using independent adversarial updates.
3d ago
RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
Post-training method enabling LLMs to retrieve and reason over long-context information effectively.
3d ago
Envisioning the Future, One Step at a Time
Video prediction model representing scene dynamics as sparse point trajectories for efficient future frame synthesis.
3d ago
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Framework for training LLMs to make evidence-dependent predictions by grounding supervision in case-specific evidence.
3d ago
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism
Mechanistic study using weight pruning to identify unified internal mechanism LLMs use for generating harmful content.
3d ago
Task-Distributionally Robust Data-Free Meta-Learning
Data-free meta-learning robustness analysis examining failure modes when learning from pre-trained models without training data.
3d ago
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
MARL method using temporal sparse coordination graphs to improve agent cooperation from historical experiences.
3d ago
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning coordination via graph structures capturing higher-order group relationships.
3d ago
Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture
Self-supervised learning for ECG signal representation using masked modeling in medical domain.
3d ago
FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening
GNN scalability method using graph coarsening to reduce inference-time computational costs.
3d ago
Graph Defense Diffusion Model
Diffusion model approach for defending graph neural networks against adversarial attacks.
3d ago
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
Graph neural network architecture using Mamba state space models to address over-smoothing in deep GNNs.
3d ago
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Method using low-rank techniques for Bayesian uncertainty quantification in neural networks via Laplace approximation.
3d ago
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
Research on polysemanticity in LLMs showing neurons encode multiple concepts, challenging discrete attribution methods for model interpretability.
3d ago
Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling
Research on reducing class bias in balanced datasets using hardness-based resampling instead of frequency-based methods.
3d ago
Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning
Federated continual fine-tuning with low-rank residual adaptation, enabling efficient parameter-efficient learning across new classes in federated settings.
3d ago
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Proxy model framework for efficient post-hoc interpretability of LLMs, reducing computational costs of model-agnostic explanations.
3d ago
Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos
Theoretical analysis of OPTQ/GPTQ post-training quantization for LLMs, providing rigorous quantitative guarantees for PTQ algorithms.
3d ago
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
Kolmogorov-Arnold networks with autoregressive weights for time series forecasting, extending comparisons beyond LLMs and FNNs.
3d ago
STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
Spatial-temporal weather forecasting with adaptive boundary alignment for regional integration from global atmosphere predictions.
3d ago
On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
Configuration-aware LoRA adaptation for quantized LLMs enabling efficient edge device deployment with heterogeneous capabilities.
3d ago
Large Reasoning Models Learn Better Alignment from Flawed Thinking
RECAP: RL method for safety alignment in large reasoning models, teaching critical evaluation of flawed premises via counter-aligned prefilling.
3d ago
Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods
Open dataset of batch distillation experiments for developing ML anomaly detection methods in chemical processes.
3d ago
Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study
Machine learning models for metabolic liver disease prediction from EHR data, comparing LASSO, random forests, and neural networks.
3d ago
LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
LLM-based flight delay prediction integrating textual aeronautical data and aircraft trajectories for air traffic management.
3d ago
Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
Graph neural network architecture using selective state space modeling to address over-smoothing in deep GNNs via node-specific representation evolution.
3d ago
Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics
Optimization of continuous attractor neural networks for brain-inspired path integration, reducing computational redundancy in navigation systems.
3d ago
AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
Vision-Language-Action model with active visual attention for robotic manipulation, extending from Markov to partially observable decision processes.
3d ago
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Analysis of flow-based diffusion models revealing two-stage behavior through oracle velocity fields, focusing on memorization-generalization dynamics.
3d ago
Adaptive Tuning of Parameterized Traffic Controllers via Multi-Agent Reinforcement Learning
Multi-agent RL framework for adaptive traffic signal control, replacing static controllers with learning-based optimization for complex traffic dynamics.
3d ago
Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning
Multi-agent RL for graph-based coordination with bandwidth constraints, addressing what information agents should transmit under communication limits.
3d ago
The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
Analysis of self-reflection emergence in LLMs through RL post-training, using gradient attribution to explain distinct solution generation and revision capabilities.
3d ago
Imitation Learning for Combinatorial Optimisation under Uncertainty
Imitation learning framework for combinatorial optimization problems, examining how expert demonstrations affect policy learning in sequential decision problems.
3d ago
FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
FP8 low-precision quantization for LLM reinforcement learning, addressing memory and compute bottlenecks in rollout generation with engineering and algorithmic solutions.
3d ago
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
Demonstrates layer pruning limitations for LLM reasoning tasks, showing pruned models lose algorithmic capabilities despite compression on classification tasks.