Papers

Cards List

MT-ProtBERT: Multi-task Learning ProtBERT for Intrinsically Disordered Proteins Classification with Scarce Data

arXiv cs.LG · 17h ago Cached

MT-ProtBERT is a multi-task learning model for classifying intrinsically disordered proteins under data scarcity, integrating self-supervised and biochemistry-informed tasks to outperform existing methods like PARROT.

0 favorites 0 likes

Spatiotemporal Kronecker Covariance Neural Networks

arXiv cs.LG · 17h ago Cached

This paper introduces Kronecker coVariance Neural Networks (KVNNs), a temporal graph neural network that decouples spatial and temporal dependencies using Kronecker products to improve spatiotemporal data analysis, addressing limitations of traditional methods like ST-PCA.

0 favorites 0 likes

Topological Signal Processing With Unoriented Operators

arXiv cs.LG · 17h ago Cached

This paper introduces an unoriented topological signal processing (TSP) framework using unoriented incidence matrices, proposes an interaction-order decomposition, and demonstrates its effectiveness in signal reconstruction tasks on real-world data.

0 favorites 0 likes

Correcting Within-Group Self-Selection Bias in Prioritized Replay

arXiv cs.LG · 17h ago Cached

This paper identifies within-group self-selection bias in prioritized experience replay and proposes sibling-aware methods to correct outcome distribution distortion, improving learning efficiency in reinforcement learning.

0 favorites 0 likes

Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers

arXiv cs.LG · 17h ago Cached

This paper introduces a benchmark for evaluating LLM agents as forward-deployed engineers in post-training delivery, highlighting the critical 'trains but does not learn' failure mode where models optimize without actual learning.

0 favorites 0 likes

Multi-Term Fourier Graph Neural Network with Sample Relationship Learning for Enhanced Remaining Useful Life Prediction

arXiv cs.LG · 17h ago Cached

The paper proposes a Multi-Term Fourier Graph Neural Network with Sample Relationship Learning (MTFGN-SRL) to enhance remaining useful life prediction by using frequency domain analysis and learning inter-sample relationships, addressing limitations in current spatio-temporal graph neural networks.

0 favorites 0 likes

Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

arXiv cs.LG · 17h ago Cached

The paper identifies sequential reappearance as a failure mode in diffusion data-point unlearning and proposes a sharpness-guided method to improve forgetting persistence across deletion sequences.

0 favorites 0 likes

Learning Neural Feedback Linearization for Data-driven Systems via Augmented Lagrangian

arXiv cs.LG · 17h ago Cached

The paper proposes a data-driven framework for feedback linearization control using neural Lie derivatives and augmented Lagrangian, with theoretical stability guarantees validated on a DC motor system.

0 favorites 0 likes

Exposing Blind Spots in Deep Imbalanced Regression Evaluation

arXiv cs.LG · 17h ago Cached

This paper identifies blind spots in evaluating deep imbalanced regression, proposing balanced metrics and showing high tail-region instability across random seeds.

0 favorites 0 likes

Dual-GNN Multilevel Coarsening for Maximum Independent Set

arXiv cs.LG · 17h ago Cached

The paper proposes a Dual-GNN Multilevel Coarsening framework to solve the maximum independent set problem efficiently by combining graph neural networks with combinatorial search, achieving near-optimal solutions with significant speedup on benchmark graphs.

0 favorites 0 likes

Brain-Inspired Hierarchical Modularity for General Continual Learning

arXiv cs.LG · 17h ago Cached

The paper proposes a brain-inspired hierarchical modular approach for continual learning to handle online and uncertain data streams, achieving significant performance gains in tasks like embodied manipulation by leveraging pretrained foundation models.

0 favorites 0 likes

Stable Unsupervised Continual Chunking with Sheaf SyncMap

arXiv cs.LG · 17h ago Cached

This paper introduces sheaf regularization to stabilize Decentralized SyncMap for unsupervised continual chunking, achieving higher normalized mutual information and better adaptation to input distribution shifts.

0 favorites 0 likes

The Probabilistic Structure of Large Language Models

arXiv cs.LG · 17h ago Cached

The paper provides a unified probabilistic framework for large language models, describing them through probability measures, training via maximum-likelihood estimation, and text generation as stochastic simulation, with insights into phenomena like hallucination and the role of diffusion models.

0 favorites 0 likes

Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow

arXiv cs.LG · 17h ago Cached

This paper introduces LEDFlow, an entropy-guided sampler for uniform discrete flow that improves generation accuracy by adaptively ordering predictions based on local entropy, with gains on reasoning, image generation, and multimodal tasks.

0 favorites 0 likes

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach

arXiv cs.LG · 17h ago Cached

This paper evaluates federated learning for privacy-preserving hybrid quantum-classical machine learning, demonstrating improved accuracy over local training while reducing communication and maintaining parameter efficiency.

0 favorites 0 likes

"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It

arXiv cs.LG · 17h ago Cached

The study reveals that chat templates control whether language models adopt a disclaimer voice (e.g., 'I'm just an AI') or an experiential voice (e.g., 'I feel'), and identifies an activation direction that can steer this behavior, impacting AI safety research.

0 favorites 0 likes

Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation

arXiv cs.CL · 17h ago Cached

This paper proposes modality-gated deep adapters to extend frozen multimodal embedding models with new modalities while preserving existing outputs bit-for-bit, demonstrated with audio and thermal packs that improve benchmark performance.

0 favorites 0 likes

PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI

arXiv cs.AI · 17h ago Cached

PhysAI-Bench is a benchmark for evaluating LLM-based agentic decision-making in autonomous UAV systems, comprising over 10,000 standardized instances and evaluating 29 foundation models.

0 favorites 0 likes

Magnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression

arXiv cs.CL · 17h ago Cached

The paper introduces Magnitude Profile (MP) scoring, a calibration-free method for pruning attention heads in transformers, achieving better perplexity on models like OPT-6.7B and RoBERTa-large compared to existing methods, with zero forward passes or calibration data.

0 favorites 0 likes

Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment

arXiv cs.AI · 17h ago Cached

This paper distinguishes between aligning AI with human preferences versus human behavior, showing that preference alignment can reduce human-likeness and establishing a Turing-test gap in current alignment methods.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback