arXiv:2601.18814v1 Announce Type: cross Abstract: Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced […]
Smooth embeddings in contracting recurrent networks driven by regular dynamics: A synthesis for neural representation
arXiv:2601.19019v1 Announce Type: new Abstract: Recurrent neural networks trained for time-series prediction often develop latent trajectories that preserve qualitative structure of the dynamical systems generating their inputs. Recent empirical work has documented topology-preserving latent organization in trained recurrent models, and recent theoretical results in reservoir computing establish conditions under which the synchronization map is an […]
Differential Voting: Loss Functions For Axiomatically Diverse Aggregation of Heterogeneous Preferences
arXiv:2601.18824v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) implicitly aggregates heterogeneous human preferences into a single utility function, even though the underlying utilities of the participants are in practice diverse. Hence, RLHF can be viewed as a form of voting, where the aggregation mechanism is defined by the loss function. Although Arrow’s […]
TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
arXiv:2601.19739v1 Announce Type: cross Abstract: Fine tuning has been regarded as a de facto approach for adapting large language models (LLMs) to downstream tasks, but the high training memory consumption inherited from LLMs makes this process inefficient. Among existing memory efficient approaches, activation-related optimization has proven particularly effective, as activations consistently dominate overall memory consumption. […]
Schema-based active inference supports rapid generalization of experience and frontal cortical coding of abstract structure
arXiv:2601.18946v1 Announce Type: new Abstract: Schemas — abstract relational structures that capture the commonalities across experiences — are thought to underlie humans’ and animals’ ability to rapidly generalize knowledge, rebind new experiences to existing structures, and flexibly adapt behavior across contexts. Despite their central role in cognition, the computational principles and neural mechanisms supporting schema […]
The role of self-supervised pretraining in differentially private medical image analysis
arXiv:2601.19618v1 Announce Type: cross Abstract: Differential privacy (DP) provides formal protection for sensitive data but typically incurs substantial losses in diagnostic performance. Model initialization has emerged as a critical factor in mitigating this degradation, yet the role of modern self-supervised learning under full-model DP remains poorly understood. Here, we present a large-scale evaluation of initialization […]
Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing
arXiv:2511.12529v2 Announce Type: replace-cross Abstract: Large Language Models have seen expanding application across domains, yet their effectiveness as assistive tools for scientific writing – an endeavor requiring precision, multimodal synthesis, and domain expertise – remains insufficiently understood. We examine the potential of LLMs to support domain experts in scientific writing, with a focus on abstract […]
daVinci-Dev: Agent-native Mid-training for Software Engineering
arXiv:2601.18418v2 Announce Type: replace-cross Abstract: Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously navigate, edit, and test complex repositories. While post-training methods have become the de facto approach for code agents, **agentic mid-training**-mid-training (MT) on large-scale data that mirrors authentic […]
Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning
arXiv:2510.02091v4 Announce Type: replace Abstract: Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow evaluations and may overlook important aspects of model behavior. In this work, we present a systematic […]
RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
arXiv:2505.14140v3 Announce Type: replace Abstract: Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including Chain/Tree/Graph-of-Thought(s), successfully improve the performance, as they are fairly cost-effective by guiding reasoning through sophisticated logical structures without modifying LLMs’ parameters. However, these manually predefined, task-agnostic […]
Large Multimodal Models for Low-Resource Languages: A Survey
arXiv:2502.05568v3 Announce Type: replace-cross Abstract: In this survey, we systematically analyze techniques used to adapt large multimodal models (LMMs) for low-resource (LR) languages, examining approaches ranging from visual enhancement and data creation to cross-modal transfer and fusion strategies. Through a comprehensive analysis of 117 studies across 96 LR languages, we identify key patterns in how […]
Intrinsic Limits of Read Trimming in Single-Stranded Bisulfite Sequencing
arXiv:2601.19002v1 Announce Type: new Abstract: Single-stranded whole-genome bisulfite sequencing (ssWGBS) enables DNA methylation profiling in low-input and highly fragmented samples, including cell-free DNA, but introduces stochastic enzymatic artifacts that complicate preprocessing and downstream interpretation. In post-bisulfite library construction, Adaptase-mediated tailing blurs the boundary between biological sequence and synthetic additions, rendering read trimming a persistent source […]