Skip to content

Papers 5330 stories

arXiv stat.ML Papers

Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics

arXiv:2608.04382v1 Announce Type: cross Abstract: Gradient descent has been of particular interest in modern machine learning beyond sole focus on optimization. Implicit bias emerging from optimization,…

arXiv cs.AI Papers

FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

arXiv:2608.04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompts or…

arXiv cs.CL Papers

Enhancing Trustworthy Clinical Diagnosis Decision-Making in Large Language Models via Etiology-Aware Attention Supervision

arXiv:2508.00285v2 Announce Type: replace Abstract: Objective: Large Language Models (LLMs) have demonstrated strong capabilities in medical text understanding and generation. However, their trustworthiness in diagnosis-oriented medical…

arXiv cs.CL Papers

Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation

arXiv:2608.01953v2 Announce Type: replace Abstract: On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However,…

arXiv cs.CV Papers

Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models

arXiv:2608.04130v1 Announce Type: new Abstract: Vision-language models for autonomous driving primarily rely on cameras and LiDAR, leaving 4D radar largely unexplored as a standalone perceptual modality…

arXiv cs.LG Papers

Neural Diversity Regularizes Hallucinations in Language Models

arXiv:2510.20690v3 Announce Type: replace-cross Abstract: Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity -- decorrelated parallel representations --…

arXiv cs.LG Papers

Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition

arXiv:2608.05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident recognition from…

arXiv stat.ML Papers

When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction

arXiv:2608.04254v1 Announce Type: cross Abstract: Longitudinal prediction of Alzheimer's disease biomarkers increasingly informs clinical decisions, and a forecast is only useful if it also reports how…

arXiv stat.ML Papers

SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant

arXiv:2608.05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging. Existing vector quantization methods, such as vqSGD,…

arXiv cs.AI Papers

Monte Carlo Tree Search for Table-to-Multimodal Report Generation

arXiv:2608.04071v1 Announce Type: new Abstract: Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in…

arXiv cs.CL Papers

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

arXiv:2608.04021v1 Announce Type: new Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the…

arXiv cs.CL Papers

The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data

arXiv:2608.04268v1 Announce Type: new Abstract: Generative models trained on artificially generated data have been shown to exhibit model collapse, resulting in significant performance degradation. As synthetic…

arXiv cs.CV Papers

RUTA: Principled Visual Token Allocation via Rate-Utility Optimization

arXiv:2608.04132v1 Announce Type: new Abstract: High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the resulting long…

arXiv cs.LG Papers

HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize

arXiv:2601.03321v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging…

arXiv cs.LG Papers

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

arXiv:2608.04060v1 Announce Type: new Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural…

arXiv stat.ML Papers

Sample Complexity of Multicalibration for Multilevel Properties

arXiv:2608.04288v1 Announce Type: cross Abstract: Calibration requires a predictor to be unbiased after conditioning on its own predictions. Multicalibration asks for this guarantee simultaneously across a…

arXiv cs.AI Papers

IConFace: Fine-Grained Identity Conditioning for Reference-Aware Face Restoration

arXiv:2605.02814v2 Announce Type: replace-cross Abstract: Severe face degradation can remove person-specific evidence, making restoration underdetermined. A generative prior may recover a sharp, plausible face yet miss…

arXiv cs.CL Papers

Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs

arXiv:2608.04759v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inconsistent with the…

arXiv cs.CL Papers

DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech

arXiv:2607.04140v2 Announce Type: replace-cross Abstract: Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness, since local errors…

arXiv cs.CV Papers

Teaching Foundation Models to Read mmWave: Pose-Guided Kinematic Representation for Human Behavior Understanding

arXiv:2608.04127v1 Announce Type: new Abstract: Large language model agents need to perceive human behavior in physical environments. Millimeter-wave (mmWave) radar provides a privacy-friendly and contactless sensing…

arXiv cs.LG Papers

The Hamilton-Jacobi Theory of Deep Learning

arXiv:2605.28983v2 Announce Type: replace Abstract: In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects…

arXiv cs.LG Papers

Prototype-based Self-Supervised Multimodal Learning for PPG and Accelerometry Signals

arXiv:2510.09764v2 Announce Type: replace Abstract: Modeling multi-modal time-series data is critical for capturing system-level dynamics, particularly in biosignals where modalities such as ECG, PPG, EDA, and…

arXiv stat.ML Papers

Statistical Mechanics of Learning on Product Wasserstein Manifolds

arXiv:2608.01434v1 Announce Type: cross Abstract: Normally the statistical mechanics of learning treats constraints on weight distributions as restrictions that shrink the space of possible solutions. Therefore,…

arXiv cs.AI Papers

Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent

arXiv:2608.04232v1 Announce Type: new Abstract: Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the others.…