arXiv Machine Learning
Aug 13
MMLA: How Memory Lets the Past Shape the Future
arXiv:2606. 28876v3 Announce Type: replace-cross Abstract: Proposal.
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
Aug 13
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
arXiv:2608. 11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents $N$, not the cognition of any single agent.
arXiv AI
Aug 13
Forecasting Side Effects of Activation Steering
arXiv:2608. 11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining.
arXiv AI
Aug 13
From Monolithic to Modular: Segment-level Automatic Prompt Optimization
arXiv:2608. 11219v1 Announce Type: new Abstract: Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others.
arXiv Machine Learning
Aug 13
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
arXiv:2608. 11829v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning.
arXiv AI
Aug 13
Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads
arXiv:2608. 11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings.
arXiv AI
Aug 13
When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
arXiv:2608. 11715v1 Announce Type: cross Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings.
arXiv AI
Aug 13
Do You See What You Draw? A Semantic Closed-Loop Framework for Holistic Evaluation of Unified Multimodal Models
arXiv:2608. 11907v1 Announce Type: cross Abstract: As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge.
arXiv AI
Aug 13
Evaluating LLM Generated Detection Rules in Cybersecurity
arXiv:2509. 16749v1 Announce Type: cross Abstract: LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners.
arXiv AI
Aug 13
LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
arXiv:2608. 11847v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) integrate visual perception with language generation, enabling responses that span image understanding and complex reasoning.
arXiv AI
Aug 13
AgenticTwin: An Agentic LLM Framework Integrated with Digital Twin for Anomaly Detection
arXiv:2608. 11679v1 Announce Type: new Abstract: Digital twins are increasingly used to monitor and simulate the behavior of cyber-physical systems.
arXiv AI
Aug 13
Accuracy and Order Sensitivity Diverge Under Label-Free Strategies
arXiv:2608. 11947v1 Announce Type: cross Abstract: Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge.
arXiv AI
Aug 13
MOON: Multi-Objective OrthoNormalized Updates for Multitask Learning
arXiv:2608. 11749v1 Announce Type: cross Abstract: Multi-objective optimization (MOO) has demonstrated significant success in multi-task learning by mitigating task conflicts through gradient manipulation.
arXiv Machine Learning
Aug 13
CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models
arXiv:2608. 10010v2 Announce Type: replace Abstract: Low-precision formats usually optimize scalar fidelity while inheriting conventional product arithmetic.
arXiv Machine Learning
Aug 13
Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP
arXiv:2608. 12086v1 Announce Type: cross Abstract: Vision-language models, such as contrastive language-image pre-training (CLIP)-based approaches, have reached state-of-the-art (SOTA) results in medical artificial intelligence.
arXiv AI
Aug 13
Commonsense on Demand: Generating and Selectively Integrating Commonsense Knowledge for Natural Language Inference
arXiv:2507. 15100v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) determines whether a premise entails, contradicts, or is neutral with respect to a hypothesis.
arXiv AI
Aug 13
From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices
arXiv:2608. 12025v1 Announce Type: cross Abstract: Medical devices are becoming more software-intensive, connected, and AI-enabled.
arXiv AI
Aug 13
Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning
arXiv:2608. 11705v1 Announce Type: new Abstract: Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones.
arXiv AI
Aug 13
Conflict and Congruency Effects in Large Language Models: In-Weight and In-Context Competition in a Verbal Conflict Task
arXiv:2608. 11510v1 Announce Type: cross Abstract: Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic basis is not fully understood.
arXiv AI
Aug 13
Learning from Online User Feedback for Shopping Agents
arXiv:2608. 11604v1 Announce Type: new Abstract: Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents.