arXiv AI
Jul 20
CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data
arXiv:2607. 16122v1 Announce Type: new Abstract: Evaluations should do more than measure a models current performance.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Jul 20
Knowledge-Centric Agents for Workflow Generation
arXiv:2607. 15845v1 Announce Type: new Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions.
arXiv AI
Jul 20
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
arXiv:2607. 14186v2 Announce Type: replace-cross Abstract: Synthesizing training data to scale agent capabilities in LLM post-training is bottlenecked by substrate-bound task synthesis: tasks are generated from fixed tools, repositories, or skill graphs, so expanding coverage requires manual substrate engineering, transferring to a new domain demands bespoke infrastructure, and the resulting distributions inherit substrate biases rather than reflecting real-world demand.
arXiv AI
Jul 20
Revisiting data-driven dynamic security assessment with a tabular foundation model
arXiv:2607. 16031v1 Announce Type: cross Abstract: Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning.
Hugging Face Trending Papers
Jul 20
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens.
Hugging Face Trending Papers
Jul 20
Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction
Recovering high dynamic range (HDR) radiance from a single standard dynamic range (SDR) image is highly ill-posed. Extreme luminance variation and severe quantization in dark regions make accurate reconstruction challenging, often leading to visual artifacts and color distortions.
arXiv Machine Learning
Jul 17
XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation
arXiv:2607. 14287v1 Announce Type: cross Abstract: Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions.
arXiv AI
Jul 17
Gate-Zero Growth: A Geometric Framework for Function-Preserving Continual Learning
arXiv:2607. 14571v1 Announce Type: cross Abstract: We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate.
arXiv Machine Learning
Jul 17
GenTL: A General Transfer Learning Model for Building Thermal Dynamics
arXiv:2501. 13703v2 Announce Type: replace-cross Abstract: Transfer Learning (TL) is an emerging field in modeling building thermal dynamics.
arXiv AI
Jul 17
Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology
arXiv:2607. 14581v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation.
arXiv AI
Jul 17
QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL
arXiv:2406. 10593v3 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks.
arXiv Machine Learning
Jul 17
Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion
arXiv:2607. 14371v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share.
arXiv AI
Jul 17
Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening
arXiv:2607. 15047v1 Announce Type: cross Abstract: Mild Cognitive Impairment is a critical early stage of cognitive decline that frequently precedes Alzheimer's disease, yet its automated detection from neuropsychological drawing tests remains fundamentally constrained by data scarcity, class imbalance, and diagnostic ambiguity near clinical boundaries.
arXiv AI
Jul 17
Interpretable Language Model for Closed-Loop Type 1 Diabetes Control
arXiv:2607. 14126v1 Announce Type: new Abstract: Type 1 Diabetes (T1D) is a chronic, life-threatening autoimmune condition characterized by the complete destruction of insulin-producing pancreatic beta cells.
arXiv Machine Learning
Jul 17
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
arXiv:2607. 14895v1 Announce Type: new Abstract: Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding.
arXiv AI
Jul 17
Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards
arXiv:2607. 14506v1 Announce Type: cross Abstract: While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood.
arXiv AI
Jul 17
An offline approach to fNIRS-guided reinforcement learning for robot behavior
arXiv:2607. 14393v1 Announce Type: cross Abstract: Human-in-the-loop Reinforcement Learning has become a popular approach to training, finetuning, and aligning robot behavior with user preferences.
arXiv AI
Jul 17
VideoSEMA: a scalable and efficient Mamba-like attention for video understanding
arXiv:2607. 14711v1 Announce Type: cross Abstract: We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time.
arXiv Machine Learning
Jul 17
On-Policy Delta Distillation
arXiv:2607. 15161v1 Announce Type: new Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model.
arXiv AI
Jul 17
Mixtures of SubExperts for Large Language Continual Learning
arXiv:2511. 06237v2 Announce Type: replace-cross Abstract: Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.