arXiv Machine Learning
Jul 7
Pathways of Visual Information Flow in Vision-Language Models
arXiv:2607. 03358v1 Announce Type: cross Abstract: We study how visual information is routed in vision-language models (VLMs).
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
Jul 7
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
arXiv:2603. 18482v2 Announce Type: replace-cross Abstract: Standard decoding strategies for text generation, including top-$k$, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting outputs to high-probability regions.
arXiv AI
Jul 7
Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation
arXiv:2605. 01790v2 Announce Type: replace-cross Abstract: A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that reconstruct fine details.
arXiv AI
Jul 7
The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
arXiv Machine Learning
Jul 7
Gradient Descent as Implicit EM in Distance-Based Neural Models
arXiv:2512. 24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking.
arXiv Machine Learning
Jul 7
Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models
arXiv:2409. 16663v5 Announce Type: replace-cross Abstract: We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving.
arXiv AI
Jul 7
SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images
arXiv:2208. 00657v2 Announce Type: cross Abstract: Building detection and change detection using remote sensing images can help urban and rescue planning.
arXiv AI
Jul 7
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
arXiv:2607. 02574v1 Announce Type: cross Abstract: The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor.
arXiv AI
Jul 7
Out-of-Distribution Generalization of Risk Aversion in Language Models
arXiv:2607. 02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned.
arXiv AI
Jul 7
SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction
arXiv:2607. 04119v1 Announce Type: cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing.
arXiv AI
Jul 7
Scalable Semantic Steering of Embedding Projections
arXiv:2607. 03978v1 Announce Type: cross Abstract: Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relationships.
arXiv AI
Jul 7
Context Tuning for In-Context Optimization
arXiv:2507. 04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates.
arXiv AI
Jul 7
Human-like Object Grouping in Self-supervised Vision Transformers
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
arXiv AI
Jul 7
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
arXiv:2507. 15903v2 Announce Type: replace-cross Abstract: Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment.
arXiv AI
Jul 7
Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models
arXiv:2607. 05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows.
arXiv AI
Jul 7
Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models
arXiv:2607. 02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information.
arXiv AI
Jul 7
MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents
arXiv:2607. 02879v1 Announce Type: new Abstract: Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query.
arXiv AI
Jul 7
Rethinking On-Policy Self-Distillation for Thinking Models
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
arXiv AI
Jul 7
Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild
arXiv:2607. 03316v1 Announce Type: cross Abstract: Agentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet there is limited empirical evidence on how developers respond to such comments in practice.
arXiv AI
Jul 7
Silicon Sampling via Cross-Survey Transfer
arXiv:2607. 03091v1 Announce Type: new Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research.