arXiv AI
Aug 13
Representation Finetuning for Continual Learning
arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Aug 13
When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits
arXiv:2608. 11560v1 Announce Type: new Abstract: Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning.
arXiv Machine Learning
Aug 13
Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes
arXiv:2608. 11390v1 Announce Type: new Abstract: Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value.
arXiv Machine Learning
Aug 13
Generative Learning for Quantum Measurement Design
arXiv:2608. 11396v1 Announce Type: cross Abstract: Extracting quantum information from a quantum state is a fundamental task of quantum computation, often requiring the estimation of many non-commuting observables under a finite measurement budget.
arXiv Machine Learning
Aug 13
Large-scale AI-Ready Data for Anti-Cancer Drug Response Modeling
arXiv:2608. 11444v1 Announce Type: cross Abstract: Drug response prediction (DRP) models are an active area of research in pharmacogenomics, with growing potential to accelerate the identification of effective anticancer drugs.
arXiv Machine Learning
Aug 13
Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
arXiv:2510. 17543v3 Announce Type: replace Abstract: Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging.
arXiv AI
Aug 13
TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation
arXiv:2608. 11236v1 Announce Type: cross Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue evidence supports the judgment.
arXiv AI
Aug 13
Teaching agentic AI to learn expert reasoning for rare disease diagnosis
arXiv:2606. 16149v3 Announce Type: replace Abstract: Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer; off-the-shelf large language models (LLMs) rank the correct disease first in only 35.
arXiv AI
Aug 13
Locating and Controlling Implicit Personalization in Large Language Models
arXiv:2608. 11735v1 Announce Type: cross Abstract: Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity.
arXiv AI
Aug 13
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
arXiv:2608. 11562v1 Announce Type: cross Abstract: Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks.
arXiv AI
Aug 13
Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
arXiv AI
Aug 13
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval
arXiv:2608. 11584v1 Announce Type: new Abstract: Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.
arXiv AI
Aug 13
The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance
arXiv:2608. 11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem.
arXiv AI
Aug 13
FM-LLM: A frequency-enhanced mixture-of-experts framework for adapting LLMs to time series forecasting
arXiv:2608. 11623v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting.
arXiv AI
Aug 13
AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research
arXiv:2608. 11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments.
arXiv AI
Aug 13
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
arXiv:2608. 12262v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration.
arXiv AI
Aug 13
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
arXiv:2608. 12253v1 Announce Type: cross Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior.
arXiv Machine Learning
Aug 13
JAPE: Joint Anomaly Prediction and Intrinsic Explanation in Multivariate Time Series
arXiv:2608. 11801v1 Announce Type: new Abstract: Multivariate time-series anomaly prediction aims to identify whether and when anomalies will occur over a future horizon from historical observations.
arXiv Machine Learning
Aug 13
Cross-Corpus Evaluation of Generalizable Vulnerability Detection in IoT Firmware
arXiv:2608. 11492v1 Announce Type: cross Abstract: IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in existing benchmarks.
arXiv Machine Learning
Aug 13
Benchmarking Cyberattack Detection in Electric Vehicle Charging Infrastructure with Benign User Updates
arXiv:2608. 11286v1 Announce Type: cross Abstract: Cyberattack detection in electric vehicle charging infrastructure is complicated by legitimate post-activation revisions to requested energy and departure time.