arXiv Machine Learning
Jun 24
RoPE-Aware Bit Allocation for KV-Cache Quantization
arXiv:2606. 24033v1 Announce Type: new Abstract: Existing low-bit KV-cache quantizers often treat each cached key as a flat vector.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv Machine Learning
Jun 24
3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy
arXiv:2606. 23964v1 Announce Type: new Abstract: Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells.
arXiv AI
Jun 24
AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach
arXiv:2606. 24655v1 Announce Type: cross Abstract: The explosive growth and complexity of product data within the dynamic Brazilian e-commerce landscape demand robust and specialized methods for structured information extraction.
arXiv AI
Jun 24
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
arXiv:2606. 23700v1 Announce Type: cross Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content.
arXiv Machine Learning
Jun 24
L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models
arXiv:2606. 24825v1 Announce Type: cross Abstract: Part-of-Speech (POS) tagging is a foundational NLP task underpinning machine translation, information extraction, and syntactic parsing.
arXiv Machine Learning
Jun 24
Learning the Koopman Operator using Attention Free Transformers
arXiv:2606. 23957v1 Announce Type: new Abstract: Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, continuous spectra, or strong transients.
arXiv AI
Jun 24
A Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy
arXiv:2606. 24115v1 Announce Type: cross Abstract: Vision-language models (VLMs) are prone to hallucination, which remains a major barrier to their safe deployment in clinical practice.
arXiv AI
Jun 24
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.
arXiv AI
Jun 24
Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction
arXiv:2606. 23830v1 Announce Type: cross Abstract: Molecular surfaces encode the geometric and physicochemical patterns that determine antibody-antigen recognition, central to epitope prediction.
arXiv AI
Jun 24
Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code
arXiv:2606. 23690v1 Announce Type: cross Abstract: Autoregressive (AR) language models have driven significant progress in automated software engineering, enabling powerful code generation and assistance systems.
arXiv AI
Jun 24
Quantifying Prior Dominance in RAG Systems
arXiv:2606. 23695v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet current evaluations rely on discrete heuristics that suffer from ''epistemic blindness'' - failing to distinguish genuine contextual information extraction from parametric memory recall.
arXiv AI
Jun 24
VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
arXiv:2606. 24124v1 Announce Type: new Abstract: Multi-step reasoning with Chain-of-Thought (CoT) prompting remains fragile: logical errors or hallucinations in early steps silently propagate, producing confident but incorrect conclusions.
arXiv AI
Jun 24
Maestro Order: A Model-Agnostic Orchestration Harness
arXiv:2606. 23983v1 Announce Type: cross Abstract: A single forward pass of a capable model is a fast, fluent, and unreliable problem-solver: it is right often enough to be useful and wrong often enough to be dangerous; in language models, such confident errors are known as hallucinations.
arXiv Machine Learning
Jun 24
Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search
arXiv:2606. 23739v1 Announce Type: new Abstract: We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem.
arXiv Machine Learning
Jun 24
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
arXiv:2606. 24133v1 Announce Type: new Abstract: The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training.
arXiv AI
Jun 24
Probing the Misaligned Thinking Process of Language Models
arXiv:2606. 24251v1 Announce Type: new Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation.
arXiv Machine Learning
Jun 24
A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR
arXiv:2604. 00725v2 Announce Type: replace-cross Abstract: End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts.
arXiv AI
Jun 24
MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching
arXiv:2606. 24433v1 Announce Type: cross Abstract: Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied.
arXiv AI
Jun 24
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
arXiv:2605. 01482v3 Announce Type: replace Abstract: Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains.
arXiv AI
Jun 24
VeriPilot: An LLM-Powered Verilog Debugging Framework
arXiv:2606. 23759v1 Announce Type: cross Abstract: Verilog debugging remains one of the most time-consuming stages in digital circuit design.