arXiv AI
Jun 2
BRo-JEPA: Learning Modular Arithmetic in Latent Space
arXiv:2606. 01372v1 Announce Type: cross Abstract: Can neural networks learn abstract algebraic rules, or do they merely memorize training patterns?
Retrieval-augmented generation
Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv AI
Jun 2
Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints
arXiv:2604. 01841v2 Announce Type: replace Abstract: Clinical prediction from structured electronic health records (EHRs) is challenging due to high dimensionality, heterogeneity, class imbalance, and distribution shift.
arXiv AI
Jun 2
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
arXiv:2606. 01024v1 Announce Type: cross Abstract: Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step budget, standard methods can generate a short, high-quality output, or they can produce long but repetitive text.
arXiv AI
Jun 2
Experiments in Agentic AI for Science
arXiv:2605. 26305v2 Announce Type: replace Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows.
arXiv AI
Jun 2
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
arXiv:2606. 00262v1 Announce Type: cross Abstract: InfoNCE is the standard contrastive learning objective, but its softmax form is not only a computational convenience: it also encodes a statistical assumption about how the top-scoring example is selected.
arXiv AI
Jun 2
MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
arXiv:2606. 00610v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge.
arXiv AI
Jun 2
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
arXiv:2605. 17034v2 Announce Type: replace-cross Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals.
arXiv AI
Jun 2
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
arXiv:2606. 00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions.
arXiv AI
Jun 2
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
arXiv:2601. 21444v2 Announce Type: replace-cross Abstract: The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs).
arXiv AI
Jun 2
Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning
arXiv:2601. 09566v4 Announce Type: replace-cross Abstract: In this work, we study whether rendering Chinese characters as visual glyph images, rather than discrete token IDs as mainstream LLMs do, providing an inductive bias for character-level language modeling.
arXiv AI
Jun 2
Cross-Entropy Games and Frost Training
arXiv:2605. 27701v2 Announce Type: replace Abstract: We present Frost Training, a method for improving Monte Carlo-based policy optimization for a large family of LLM-as-a-judge tasks called Cross-Entropy Games.
arXiv AI
Jun 2
A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
arXiv:2601. 17952v2 Announce Type: replace-cross Abstract: Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer disease, where early and trustworthy predictions are essential.
arXiv Machine Learning
Jun 2
Closing the Alignment-Maturity Gap in Federated Prototype Learning
arXiv:2606. 02172v1 Announce Type: new Abstract: Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL).
arXiv AI
Jun 2
ES-Merging: Biological MLLM Merging via Embedding Space Signals
arXiv:2603. 14405v2 Announce Type: replace-cross Abstract: Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery.
arXiv AI
Jun 2
SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
arXiv:2601. 14323v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored.
arXiv Machine Learning
Jun 2
Efficient Synthetic Network Generation via Latent Embedding Reconstruction
arXiv:2606. 00934v1 Announce Type: cross Abstract: Network data are ubiquitous across the social sciences, biology, and information systems.
arXiv Machine Learning
Jun 2
Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality
arXiv:2603. 01471v2 Announce Type: replace-cross Abstract: Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification.
arXiv AI
Jun 2
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
arXiv:2606. 00153v1 Announce Type: cross Abstract: Cross-modal 2D-3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D LiDAR range-view representations.
arXiv AI
Jun 2
RuleEdit: Failure-Guided Human-AI Model Editing with Prospective Impact Preview
arXiv:2606. 00011v1 Announce Type: cross Abstract: Despite the promise of AI to assist complex decisions, practitioners still lack ways to detect likely failures and inspect the consequences of model edits before committing them.
arXiv AI
Jun 2
Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
arXiv:2507. 15336v3 Announce Type: replace-cross Abstract: Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency.