arXiv:2601.20099v1 Announce Type: cross Abstract: Humans and large language models (LLMs) now co-produce and co-consume the web’s shared knowledge archives. Such human-AI collective knowledge ecosystems contain feedback loops with both benefits (e.g., faster growth, easier learning) and systemic risks (e.g., quality dilution, skill reduction, model collapse). To understand such phenomena, we propose a minimal, interpretable […]
Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms
arXiv:2601.20131v1 Announce Type: cross Abstract: Designing an embedding retrieval system requires navigating a complex design space of conflicting trade-offs between efficiency and effectiveness. This work structures these decisions as a vertical traversal of the system design stack. We begin with the Representation Layer by examining how loss functions and architectures, specifically Bi-encoders and Cross-encoders, define […]
Certificate-Guided Pruning for Stochastic Lipschitz Optimization
arXiv:2601.20231v1 Announce Type: cross Abstract: We study black-box optimization of Lipschitz functions under noisy evaluations. Existing adaptive discretization methods implicitly avoid suboptimal regions but do not provide explicit certificates of optimality or measurable progress guarantees. We introduce textbfCertificate-Guided Pruning (CGP), which maintains an explicit emphactive set $A_t$ of potentially optimal points via confidence-adjusted Lipschitz envelopes. […]
Beyond the Needle’s Illusion: Decoupled Evaluation of Evidence Access and Use under Semantic Interference at 326M-Token Scale
arXiv:2601.20276v1 Announce Type: cross Abstract: Long-context LLM agents must access the right evidence from large environments and use it faithfully. However, the popular Needle-in-a-Haystack (NIAH) evaluation mostly measures benign span localization. The needle is near-unique, and the haystack is largely irrelevant. We introduce EverMemBench-S (EMB-S), an adversarial NIAH-style benchmark built on a 326M-token MemoryBank. While […]
DiagLink: A Dual-User Diagnostic Assistance System by Synergizing Experts with LLMs and Knowledge Graphs
arXiv:2601.20311v1 Announce Type: cross Abstract: The global shortage and uneven distribution of medical expertise continue to hinder equitable access to accurate diagnostic care. While existing intelligent diagnostic system have shown promise, most struggle with dual-user interaction, and dynamic knowledge integration — limiting their real-world applicability. In this study, we present DiagLink, a dual-user diagnostic assistance […]
LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
arXiv:2601.20375v1 Announce Type: cross Abstract: Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality samples, necessitating effective data processing (DP). In practice, DP strategies are typically developed through iterative manual analysis and trial-and-error adjustment. These processes inevitably incur high labor […]
Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations
arXiv:2601.20449v1 Announce Type: cross Abstract: Explainable Artificial Intelligence (XAI) is becoming increasingly essential for enhancing the transparency of machine learning (ML) models. Among the various XAI techniques, counterfactual explanations (CFs) hold a pivotal role due to their ability to illustrate how changes in input features can alter an ML model’s decision, thereby offering actionable recourse […]
Probabilistic Sensing: Intelligence in Data Sampling
arXiv:2601.19953v1 Announce Type: cross Abstract: Extending the intelligence of sensors to the data-acquisition process – deciding whether to sample or not – can result in transformative energy-efficiency gains. However, making such a decision in a deterministic manner involves risk of losing information. Here we present a sensing paradigm that enables making such a decision in […]
Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
arXiv:2601.19963v1 Announce Type: cross Abstract: Cross-session nonstationarity in neural activity recorded by implanted electrodes is a major challenge for invasive Brain-computer interfaces (BCIs), as decoders trained on data from one session often fail to generalize to subsequent sessions. This issue is further exacerbated in practice, as retraining or adapting decoders becomes particularly challenging when only […]
Structural Compositional Function Networks: Interpretable Functional Compositions for Tabular Discovery
arXiv:2601.20037v1 Announce Type: cross Abstract: Despite the ubiquity of tabular data in high-stakes domains, traditional deep learning architectures often struggle to match the performance of gradient-boosted decision trees while maintaining scientific interpretability. Standard neural networks typically treat features as independent entities, failing to exploit the inherent manifold structural dependencies that define tabular distributions. We propose […]
Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data
arXiv:2601.20072v1 Announce Type: cross Abstract: We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image reconstruction and classification using both unlabeled and labeled samples with dynamically selected pseudo-labels. SSMAE introduces a validation-driven gating […]
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
arXiv:2601.20103v1 Announce Type: cross Abstract: Recent advances in reinforcement learning for code generation have made robust environments essential to prevent reward hacking. As LLMs increasingly serve as evaluators in code-based RL, their ability to detect reward hacking remains understudied. In this paper, we propose a novel taxonomy of reward exploits spanning across 54 categories and […]