arXiv Machine Learning
Aug 7
KV-Skill: Forging Expertise in the Model's Native Language
arXiv:2608. 05475v1 Announce Type: new Abstract: Task knowledge is commonly stored either as text in the prompt or as an update to model weights.
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
Aug 7
Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs
arXiv:2608. 05660v1 Announce Type: new Abstract: As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practical problem.
arXiv Machine Learning
Aug 7
Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading
arXiv:2608. 05675v1 Announce Type: new Abstract: Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change.
arXiv Machine Learning
Aug 7
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
arXiv:2608. 06031v1 Announce Type: new Abstract: Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts.
arXiv Machine Learning
Aug 7
Timestep-Conditioned Transformers for Global Weather Forecasting
arXiv:2608. 06241v1 Announce Type: new Abstract: Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps.
arXiv Machine Learning
Aug 7
On-Policy Self-Distillation without Any Supervision
arXiv:2608. 06296v1 Announce Type: new Abstract: On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs).
arXiv Machine Learning
Aug 7
Safe Evolution with Circuit Anchors
arXiv:2608. 05158v1 Announce Type: cross Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential functions for survival.
arXiv Machine Learning
Aug 7
Where Privacy Risk Lives in English-Source Multilingual RAG: A Stage-Decomposed Audit Across Five Query Languages
arXiv:2608. 05163v1 Announce Type: cross Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information.
arXiv Machine Learning
Aug 7
PoolBench: A Benchmark for Pooling Strategies in Concept Representation Evaluation for Decoder-Only LLMs
arXiv:2608. 05162v1 Announce Type: cross Abstract: Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden states into a passage-level vector, yet no shared protocol exists for comparing this choice across concepts, models, and tasks.
arXiv Machine Learning
Aug 7
CLARA: Clarification of Language Ambiguity through Result Analysis for Natural-Language Cancer Genomics Queries
arXiv:2608. 05195v1 Announce Type: cross Abstract: A natural language interface can be used to make cancer genomics databases easier to use, but even if a question is perfectly fluent, its scientific meaning can be ambiguous.
arXiv Machine Learning
Aug 7
Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
arXiv:2608. 05341v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings.
arXiv Machine Learning
Aug 7
Robust Context-Aware Detection of Malicious Instructions in Text
arXiv:2608. 05430v1 Announce Type: cross Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks.
arXiv Machine Learning
Aug 7
MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health
arXiv:2506. 02260v5 Announce Type: replace-cross Abstract: Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data.
arXiv Machine Learning
Aug 7
CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis
arXiv:2507. 14022v2 Announce Type: replace-cross Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis.
arXiv Machine Learning
Aug 7
Clinician input steers AI toward accurate and harmful recommendations
arXiv:2603. 14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions.
arXiv Machine Learning
Aug 7
MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis
arXiv:2605. 00025v3 Announce Type: replace-cross Abstract: Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-impairing conditions.
arXiv AI
Aug 7
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
arXiv:2608. 05204v1 Announce Type: new Abstract: LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workflows.
arXiv AI
Aug 7
Evaluating and Improving Pedagogical Fit in LLM-Based AI Tutors with the Pedagogical Suitability Index
arXiv:2608. 05411v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as AI tutors, but a correct answer is not always a pedagogically appropriate one.
arXiv AI
Aug 7
The Ignition Index: Measuring Global Workspace Dynamics in Language Models
arXiv:2608. 05160v1 Announce Type: new Abstract: We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in transformer language models.
arXiv AI
Aug 7
Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging
arXiv:2608. 05541v1 Announce Type: new Abstract: Evolution Strategy (ES) is a promising alternative to gradient-based fine-tuning for resource-constrained Large Language Model (LLM) reasoning.