Skip to content

Papers 5471 stories

arXiv cs.CL Papers

Few-Step Diffusion Language Models via Trajectory Self-Distillation

arXiv:2602.12262v4 Announce Type: replace Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding.…

arXiv cs.CL Papers

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

arXiv:2607.02980v1 Announce Type: new Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of…

arXiv cs.CV Papers

Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies

arXiv:2607.02560v1 Announce Type: new Abstract: Pedestrian-level wind prediction is essential for urban design and wind-comfort assessment, but high-fidelity simulations such as LES remain computationally expensive for…

arXiv cs.LG Papers

Learning to Reason Efficiently with Discounted Reinforcement Learning

arXiv:2510.23486v3 Announce Type: replace Abstract: Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems…

arXiv cs.LG Papers

Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures

arXiv:2404.06294v2 Announce Type: replace-cross Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to…

arXiv cs.NE Papers

A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

arXiv:2509.08269v5 Announce Type: replace Abstract: Large language models (LLMs) are increasingly integrated with evolutionary computation to support optimization tasks. This survey primarily focuses on evolutionary optimization,…

arXiv stat.ML Papers

A Hierarchy of Policy Learning Problems

arXiv:2607.03385v1 Announce Type: new Abstract: Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making. A majority of work…

arXiv cs.AI Papers

ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability

arXiv:2607.02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from small language…

arXiv cs.CL Papers

The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models

arXiv:2604.19139v3 Announce Type: replace Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional…

arXiv cs.CL Papers

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management

arXiv:2506.01254v2 Announce Type: replace Abstract: FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character n-grams. Its…

arXiv cs.CV Papers

Do Diabetic Foot Ulcer Segmentation Models Generalize? A Cross-Dataset Benchmark of CNN and Transformer Architectures

arXiv:2607.02555v1 Announce Type: new Abstract: Deep learning models for diabetic foot ulcer (DFU) segmentation routinely report high accuracy, but they are almost always trained and tested…

arXiv cs.LG Papers

GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment

arXiv:2607.04673v1 Announce Type: cross Abstract: Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer…

arXiv cs.LG Papers

Safe Inference-Time Alignment via Lagrangian Reward Augmentation

arXiv:2607.02781v1 Announce Type: new Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However,…

arXiv cs.NE Papers

Local Learning Rules for Out-of-Equilibrium Physical Generative Models

arXiv:2506.19136v4 Announce Type: replace-cross Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient…

arXiv stat.ML Papers

Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions

arXiv:2607.03161v1 Announce Type: new Abstract: In selective deployment, practitioners act only on a model-chosen subset of individuals based on predicted conditional average treatment effects, but marginal…

arXiv cs.AI Papers

Autodata: An agentic data scientist to create high quality synthetic data

arXiv:2606.25996v3 Announce Type: replace Abstract: We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and…

arXiv cs.CL Papers

Selective Disclosure Watermarking for Large Language Models

arXiv:2607.05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for…

arXiv cs.CL Papers

psytechlab at CLPsych 2026: Utilising Natural Language Processing methods and Large Language Models for Social Media Text Analysis

arXiv:2607.03003v1 Announce Type: new Abstract: Social media posts are a rich and valuable source of data for analyzing mental health states and users' well-being using automated…

arXiv cs.CV Papers

Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction

arXiv:2607.02554v1 Announce Type: new Abstract: Sparse-view neural reconstruction is challenging in outdoor driving scenes, where cameras usually move along a narrow forward-facing trajectory and provide limited…

arXiv cs.LG Papers

Wavelet Scattering Transform for Interpretable Schizophrenia Biomarker Discovery and Classification from Resting-State EEG

arXiv:2607.05282v1 Announce Type: cross Abstract: Schizophrenia is a debilitating neuropsychiatric disorder characterized by profound cortical network dysregulation, for which objective, clinically translatable EEG based biomarkers remain…

arXiv cs.LG Papers

Induction Heads Interpolate N-Grams

arXiv:2607.02800v1 Announce Type: new Abstract: Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they implement…

arXiv cs.NE Papers

Evolutionary Ensemble of Agents

arXiv:2605.09018v3 Announce Type: replace Abstract: We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for…

arXiv stat.ML Papers

Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms

arXiv:2607.02681v1 Announce Type: new Abstract: Integrating information across related tasks can improve estimation and prediction in transfer, multi-task, and federated learning, but contamination and heterogeneity make…

HF Daily Papers Papers

Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization

Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Recent syllabic tokenization methods employ teacher-student distillation of…