arXiv AI
Jun 9
RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
arXiv:2603. 12666v2 Announce Type: replace-cross Abstract: Retrosynthesis prediction aims to identify reactants that can synthesize a given product molecule.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Jun 9
FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction
arXiv:2606. 07645v1 Announce Type: cross Abstract: The scarcity of hard negative samples in current vision-language datasets significantly hinders fine-grained perception.
arXiv Machine Learning
Jun 9
Hierarchical Projection for Adaptive Knowledge Transfer
arXiv:2606. 08691v1 Announce Type: new Abstract: Modern data-driven applications increasingly involve learning from multiple heterogeneous sources, where a target dataset is limited but related information is available across domains.
arXiv AI
Jun 9
Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy
arXiv:2606. 07929v1 Announce Type: new Abstract: Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes.
arXiv AI
Jun 9
Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings
arXiv:2509. 10534v3 Announce Type: replace-cross Abstract: The attention mechanism in a Transformer architecture matches key to query based on both content -- the what -- and position in a sequence -- the where.
arXiv AI
Jun 9
Quantifying and Optimizing Simplicity via Polynomial Representations
arXiv:2605. 29823v2 Announce Type: replace Abstract: Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization.
arXiv Machine Learning
Jun 9
Public Machine Learning Solver Framework for Novices in the Machine Learning Domain
arXiv:2606. 08212v1 Announce Type: new Abstract: Solving machine learning problems is complex and typically reserved for experts.
arXiv AI
Jun 9
Emergence of Context Characteristics Sensitivity in Large Language Models
arXiv:2606. 09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query.
arXiv AI
Jun 9
Evaluating Hallucinations in Domain-Adapted Large Language Models
arXiv:2606. 07521v1 Announce Type: cross Abstract: This study investigates the phenomenon of hallucinations in domain-adapted Large Language Models (LLMs), focusing on the fine-tuning of the Llama-2 model with the Lamini dataset.
arXiv AI
Jun 9
Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data
arXiv:2606. 08107v1 Announce Type: cross Abstract: Robotics faces a fundamental challenge of data scarcity.
arXiv AI
Jun 9
Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design
arXiv:2606. 09266v1 Announce Type: cross Abstract: Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that matches the desired response at one frequency may deviate at others, and modifying geometry to improve one sub-band often perturbs neighboring sub-bands.
arXiv AI
Jun 9
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
arXiv:2606. 07631v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task.
arXiv AI
Jun 9
Language-based Trial and Error Falls Behind in the Era of Experience
arXiv:2601. 21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.
arXiv Machine Learning
Jun 9
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
arXiv Machine Learning
Jun 9
Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models
arXiv:2606. 07522v1 Announce Type: cross Abstract: We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that have the highest magnitude of semantic shift.
arXiv Machine Learning
Jun 9
PriFT: Prior-Support Guided Supervised Fine-Tuning
arXiv:2606. 09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL.
arXiv Machine Learning
Jun 9
Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model
arXiv:2606. 09770v1 Announce Type: cross Abstract: Nearby neurons in cortex share similar response profiles, producing systematic spatial organization across sensory and cognitive systems.
arXiv Machine Learning
Jun 9
Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families
arXiv:2606. 09456v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models (LLMs) for transferring knowledge from domain experts to student models.
arXiv Machine Learning
Jun 9
From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model
arXiv:2606. 08945v1 Announce Type: new Abstract: We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large language model.
arXiv AI
Jun 9
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
arXiv:2606. 08063v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions.