arXiv:2603.11045v2 Announce Type: replace-cross Abstract: Inverse problems for stiff parabolic partial differential equations (PDEs), such as the inverse heat conduction problem (IHCP), are severely ill-posed: the forward map rapidly damps high-frequency interior structure before it reaches the boundary. Soft-constrained physics-informed neural networks (PINNs), which embed the PDE as a residual penalty, suffer from gradient pathology […]
Evolutionary Ensemble of Agents
arXiv:2605.09018v2 Announce Type: replace-cross Abstract: We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the “LLMs as optimizers” paradigm, EvE fixes the base agent substrate and focuses entirely on evolving the cumulative guidance and skills […]
A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval
arXiv:2605.14581v1 Announce Type: cross Abstract: Visual RAG has offered an alternative to traditional RAG. It treats documents as images and uses vision encoders to obtain vision patch tokens. However, hundreds of patch tokens per document create retrieval and storage challenges in a vector database. Practical deployment requires aggregating them into a single vector. This raises […]
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
arXiv:2605.11459v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models achieve remarkable flexibility and generalization beyond classical control paradigms. However, most prevailing VLAs are trained under a single-frame observation paradigm, which leaves them structurally blind to temporal dynamics. Consequently, these models degrade severely in non-stationary scenarios, even when trained or finetuned on dynamic datasets. Existing approaches either […]
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
arXiv:2605.12784v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approaches for molecular generation often suffer from high rates of invalid and low-quality ligand candidates, a result of the syntactic limitations of current models with regard to molecular strings. In […]
Vision-Core Guided Contrastive Learning for Balanced Multi-modal Prognosis Prediction of Stroke
arXiv:2605.14710v1 Announce Type: cross Abstract: Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis by integrating diverse data sources. However, accurate prognosis for ischemic stroke remains challenging due to limitations in existing multi-modal approaches. First, current methods are predominantly confined to dual-modal fusion, lacking a framework that effectively integrates the trifecta of […]
Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
arXiv:2512.11855v2 Announce Type: replace-cross Abstract: Enforcing exact symmetry in machine learning models often yields significant gains in scientific applications, serving as a powerful inductive bias. However, recent work suggests that relying on approximate symmetry can offer greater flexibility and robustness. Despite promising empirical evidence, there has been little theoretical understanding, and in particular, a direct […]
EVA: Editing for Versatile Alignment against Jailbreaks
arXiv:2605.14750v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent defenses typically rely on safety fine-tuning or external filters to reduce the model’s likelihood of producing harmful content. While […]
Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
arXiv:2603.20334v3 Announce Type: replace-cross Abstract: In high-complexity abstract reasoning, a system must infer a latent rule from a few examples or structured observations and apply it to unseen instances. LLMs can express such rules as programs, but ordinary conversation-based refinement is largely outcome-level: it observes that an answer or output is wrong without formally re-checking […]
GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning
arXiv:2605.14841v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become the dominant paradigm for parameter-efficient fine-tuning (PEFT) of large language models (LLMs). However, its bilinear structure introduces a critical limitation: the mapping from trainable parameters to weight updates is not distance-preserving, distorting the optimization landscape. Methods that project a low-dimensional vector into LoRA’s parameter space, […]
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
arXiv:2602.03814v2 Announce Type: replace Abstract: Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning — spending tokens when they improve reliability and stopping early when additional computation is unlikely to help. However, setting the token budget, as well as the threshold for adaptive reasoning, […]
Tokenizing Single-Channel EEG with Time-Frequency Motif Learning
arXiv:2502.16060v5 Announce Type: replace-cross Abstract: Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from single-channel EEG signals and encodes them into discrete tokens. We propose a dual-path architecture with time-frequency masking to […]