arXiv Machine Learning
Aug 21
Continuous Adversarial MeanFlow Transfer
arXiv:2608. 19540v1 Announce Type: new Abstract: Training fast generators on new domains with limited data remains challenging for two reasons.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Aug 21
Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions
arXiv:2608. 19710v1 Announce Type: cross Abstract: Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur.
arXiv AI
Aug 21
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
arXiv:2608. 20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost.
arXiv Computation and Language
Aug 21
A Speech Corpus for Mizo Automatic Speech Recognition: Whisper and SraVaani 1.0 Fine-Tuning with Morphology-Aware Evaluation
arXiv:2608. 19361v1 Announce Type: new Abstract: This study reports the development of an Automatic Speech Recognition (ASR) system in Mizo, a low-resource language.
arXiv Computation and Language
Aug 21
Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder
arXiv:2608. 19957v1 Announce Type: new Abstract: Natural language code retrieval is a rapidly evolving task in computer science.
arXiv AI
Aug 21
Frequency-Aware Continual Learning for Smart Contract Vulnerability Detection with Large Language Models
arXiv:2608. 19680v1 Announce Type: new Abstract: Smart contract vulnerability detection with Large Language Models (LLMs) faces three causally linked challenges.
arXiv Machine Learning
Aug 21
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
arXiv:2608. 19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage.
arXiv Computer Vision
Aug 21
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters
arXiv:2608. 19637v1 Announce Type: new Abstract: Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition.
arXiv Computer Vision
Aug 21
V-REX: Efficient Specialist VLM Training for Veterinary X-Rays
arXiv:2608. 20069v1 Announce Type: new Abstract: While generalist VLMs are expensive to train, creating domain experts is widely assumed to require fine-tuning increasingly large foundation models.
arXiv AI
Aug 21
LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
arXiv:2608. 19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead.
arXiv AI
Aug 21
Towards Audio Token Compression in Large Audio Language Models
arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.
arXiv Machine Learning
Aug 21
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
arXiv:2608. 19463v1 Announce Type: new Abstract: Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations.
arXiv AI
Aug 21
DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
arXiv:2509. 08022v3 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with diverse human values is essential for safe and effective deployment, yet existing benchmarks often overlook cultural and demographic variation.
arXiv Computer Vision
Aug 21
CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning
arXiv:2507. 09471v4 Announce Type: replace Abstract: Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.
arXiv AI
Aug 21
G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation
arXiv:2608. 20331v1 Announce Type: cross Abstract: Personalized interpretation of medical reports has emerged as an increasingly important need among patients.
arXiv Computer Vision
Aug 21
Gallileo-4D: Frozen Backbone Ensemble for Dynamic 4D Reconstruction
arXiv:2608. 19743v1 Announce Type: new Abstract: We describe our entry to the PhysAI Dynamic 4D Reconstruction Challenge, which placed third of 27 teams at 0.
arXiv AI
Aug 21
EXIMO: VLM Guided Exploration of VLA Policies
arXiv:2608. 19891v1 Announce Type: new Abstract: How to efficiently finetune robot policies to learn new tasks on the fly?
arXiv Machine Learning
Aug 21
$TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
arXiv:2608. 20326v1 Announce Type: cross Abstract: Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions.
Hugging Face Trending Papers
Aug 20
G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation
Personalized interpretation of medical reports has emerged as an increasingly important need among patients. Addressing this need requires both evidence-grounded medical factuality and context-dependent patient communication, yet existing medical vision-language tasks do not adequately capture these dual requirements.
Hugging Face Trending Papers
Aug 20
$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted.