arXiv Machine Learning
Jun 11
Attention by Synchronization in Coupled Oscillator Networks
arXiv:2606. 12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates.
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 AI
Jun 11
DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
arXiv:2511. 02627v3 Announce Type: replace Abstract: We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability.
arXiv Machine Learning
Jun 11
Counterexample Guided Learning in the Large using Reasoning Agents
arXiv:2606. 11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control.
arXiv AI
Jun 11
AVIS: Adaptive Test-Time Scaling for Vision-Language Models
arXiv:2606. 11576v1 Announce Type: cross Abstract: Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains.
arXiv AI
Jun 11
When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?
arXiv:2510. 02660v2 Announce Type: replace-cross Abstract: When researchers claim AI systems possess ToM or mental models, they are fundamentally discussing behavioral predictions and bias corrections rather than genuine mental states.
arXiv AI
Jun 11
AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable
arXiv:2606. 11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions.
arXiv AI
Jun 11
From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning
arXiv:2606. 11745v1 Announce Type: cross Abstract: Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects.
arXiv AI
Jun 11
Mapping Scientific Literature with Large Language Models and Topic Modeling
arXiv:2510. 16152v2 Announce Type: replace-cross Abstract: Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science.
arXiv AI
Jun 11
Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning
arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).
arXiv AI
Jun 11
Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness
arXiv:2606. 11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where.
arXiv Machine Learning
Jun 11
Learning Patterns and Abstractions from Perceptual Sequences
arXiv:2503. 10973v2 Announce Type: replace Abstract: Cognition swiftly breaks high-dimensional sensory streams into familiar parts and uncovers their relations.
arXiv AI
Jun 11
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
arXiv:2605. 02411v2 Announce Type: replace Abstract: A semantic gap separates how users describe tasks from how tools are documented.
arXiv AI
Jun 11
Diffusion-based Cumulative Adversarial Purification for Vision Language Models
arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.
arXiv AI
Jun 11
Are LLMs Bad at Moral Reasoning?
arXiv:2606. 11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly.
arXiv Machine Learning
Jun 11
SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation
arXiv:2606. 11304v1 Announce Type: cross Abstract: We introduce SPADE (SPlit And Delay Embeddings), an autoregressive transformer for sequences whose tokens carry multiple features.
arXiv AI
Jun 11
PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
arXiv:2606. 11262v1 Announce Type: cross Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference.
arXiv AI
Jun 11
Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security
arXiv:2606. 11671v1 Announce Type: cross Abstract: Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide.
arXiv AI
Jun 11
Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
arXiv:2606. 11205v1 Announce Type: cross Abstract: Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements.
arXiv AI
Jun 11
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
arXiv:2605. 14738v3 Announce Type: replace-cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE.
arXiv AI
Jun 11
GPO: Learning from Critical Steps to Improve LLM Reasoning
arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.