arXiv AI
Jul 29
Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning
arXiv:2607. 25299v1 Announce Type: cross Abstract: Optimization over the Stiefel manifold plays a significant role in various machine learning tasks.
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
Jul 29
Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code
arXiv:2607. 24797v1 Announce Type: cross Abstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-parietal encoding route (impaired in pure agraphia), sharing a partial orthographic core.
arXiv AI
Jul 29
Addressable Recall Compaction for Long Context-Window Control in AI Agents
arXiv:2607. 25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window.
arXiv AI
Jul 29
Specula: Scaling formal specifications for autonomous model checking of system code
arXiv:2607. 25333v1 Announce Type: cross Abstract: Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications for highly effective model checking and bug finding.
arXiv AI
Jul 29
Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis
arXiv:2607. 25554v1 Announce Type: new Abstract: Future event prediction carries broad social impact yet remains challenging.
arXiv AI
Jul 29
EviDAG: Auditable Causal DAG Authoring with Biomedical Literature
arXiv:2607. 21859v2 Announce Type: replace Abstract: Constructing causal directed acyclic graphs (DAGs) is a core step in biomedical causal analysis, yet it remains a largely manual process.
arXiv AI
Jul 29
Where Steering Signals Come From: Activation Source Selection in Activation Steering
arXiv:2607. 25270v1 Announce Type: cross Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail.
arXiv AI
Jul 29
Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?
arXiv:2607. 25995v1 Announce Type: cross Abstract: Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads.
Hugging Face Trending Papers
Jul 29
PlantBGC: Transformer for Plant BGC Discovery via Label-Free Domain Adaptation and Weak Supervision
Plant biosynthetic gene clusters (BGCs) encode specialized-metabolite pathways, yet curated plant BGC labels remain scarce, hindering supervised discovery at genome scale. Existing plant BGC mining tools are largely signature- and rule-driven and do not fully leverage recent advances in contextual representation learning for modeling long-range domain context and controlling false positives under strong domain shift.
Hugging Face Trending Papers
Jul 29
Q-Steer: Action-Value Guidance for Molecular Policy Optimization
Oracle-limited molecular optimization gives reward only after a complete molecule is generated, while each rollout requires many local next-token decisions. This delayed-feedback interface makes molecular policy optimization myopic: an optimizer can learn that a molecule was good without knowing which intermediate actions made it good.
Hugging Face Trending Papers
Jul 29
Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text
Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways. Detecting a conflict is only the first step: review workflows may also need to determine its type, since numerical, temporal, referential, factual, and normative inconsistencies require different evidence and downstream checks.
Hugging Face Trending Papers
Jul 29
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy. A standard way to balance this trade-off is via a KL-regularized RL objective, although this formulation does not by itself provide a principled way to set the regularization coefficient.
Hugging Face Trending Papers
Jul 29
Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs
Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential to perpetuate social biases and reinforce stereotypes. In this study, we investigate gender bias in LLMs through the lens of their associations with musical instruments.
OpenAI Blog
Jul 29
How GPT-5.6 fuses frontier intelligence with frontier efficiency
GPT-5. 6 improves AI efficiency across models, inference, and agentic workflows, helping deliver more useful intelligence per dollar.
Hugging Face Trending Papers
Jul 28
Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring
Context: Large Language Models (LLMs) offer natural-language flexibility for automated requirements elicitation but frequently generate structurally invalid requirements and logical inconsistencies, lacking formal correctness guarantees. Objectives: This study aims to eliminate logical inconsistencies and enforce structural conformance in LLM-generated requirements while quantifying the LLM's pre-validation decision uncertainty within a formal domain model.
Hugging Face Trending Papers
Jul 28
Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting
Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evaluate these choices using two end-to-end customer-outcome metrics rather than component accuracy: Usefulness, the fraction of turns with a shown, non-harmful, relevant response, and Harmful Exposure, the fraction with a shown harmful response.
Hugging Face Trending Papers
Jul 28
Position: Evaluation Scores Are Perishable Knowledge Claims
Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation.
Hugging Face Trending Papers
Jul 28
GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure
Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin. Recent large language models (LLMs) offer new opportunities to automate this process, yet existing LLM-based approaches generate each component through independent single-turn calls with no shared context, leaving interface mismatches undetected and reported coverage disconnected from specification requirements.
Hugging Face Trending Papers
Jul 28
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals.
Hugging Face Trending Papers
Jul 28
VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening
We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing device and sends captured images, together with optional symptom descriptions, to a server-hosted vision-language model for zero-shot disease classification.