cập nhật 47 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5178, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
Distilling Expert Judgment at Scale
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33233v1 Announce Type: new Abstract: Frontier AI models are increasingly deployed on topics where the stakes are high and expert judgment is required, including healthcare, defense, finance, governance, and politics. We present a general methodology for distilling exp…

🅲 hạng C
20
NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33240v1 Announce Type: new Abstract: As frontier AI systems increasingly serve as sources of political and current-events information, evaluating the epistemic quality of their responses is now especially consequential. Existing evaluations often focus narrowly on ide…

🅲 hạng C
20
AI Teaches Humans to Handle Complexity in the Game of Go
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33323v1 Announce Type: new Abstract: Strategic decision-making in complex environments requires balancing local stability against global coordination. Using the game of Go as a bounded empirical testbed, we investigate how biological and artificial agents navigate thi…

🅲 hạng C
20
TempShap: When and How Much a Feature Matters in Time-Series Forecasting
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33330v1 Announce Type: new Abstract: Attribution for a time-series forecaster should answer two questions that a feature-level scalar cannot: when in the input window a feature acts, and how much its influence changes across the forecast horizon. Most existing Shapley…

🅲 hạng C
20
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33355v1 Announce Type: new Abstract: Molecular cloning is one of the most routine wet-lab workflows, yet existing evaluations of language models in biology mostly test knowledge recall or isolated steps rather than end-to-end experimental planning. We introduce BenchB…

🅲 hạng C
20
Data Optimization for LLMs: A Survey
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33405v1 Announce Type: new Abstract: Large language models (LLMs) have attracted great attention in both academic and industrial communities in recent years. Numerous survey studies have covered various aspects of LLMs, such as learning strategies, applications, align…

🅲 hạng C
20
A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training Alignment
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33451v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) and multimodal LLMs (MLLMs) arise from the synergy of the full training pipeline, including data and tokenization, pretraining, and post-training (supervised fine-tuning, preference …

🅲 hạng C
20
FraudSociety: A Generative Agent-Based Society for the Financial-Fraud Economy
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33536v1 Announce Type: new Abstract: Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such large-scale harm requires jointly modeling informational and f…

🅲 hạng C
20
Counterfactual Model Testing Under Distribution Shift
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33594v1 Announce Type: new Abstract: Deployed machine learning (ML) models can degrade as the distribution of their input data shifts. Such shifts can result from changes in the population or from data integrity issues in the pipeline that materializes model features,…

🅲 hạng C
20
RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33625v1 Announce Type: new Abstract: Multi-Head Latent Attention (MLA) has been adopted by recent frontier large language models. Instead of per-head keys and values, MLA caches a compressed KV latent that is up-projected into keys and values at decode time, together …

🅲 hạng C
20
TAD: Distilling Vision-Language-Action Policies from Teacher Trajectories Alone
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.33650v1 Announce Type: new Abstract: Online distillation of vision-language-action (VLA) policies commonly relies on teacher action scores that an inference-only interface may not expose. Trajectory-only Adversarial Distillation (\gad{}) instead turns a fixed bank of …

🅲 hạng C
20
Counting the Bandages: On measuring the time that AI saves
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.35942v1 Announce Type: new Abstract: I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the…

🅲 hạng C
20
Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36169v1 Announce Type: new Abstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixe…

🅲 hạng C
20
Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36183v1 Announce Type: new Abstract: We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rat…

🅲 hạng C
20
BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36239v1 Announce Type: new Abstract: Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-te…

🅲 hạng C
20
A Smart Instant Book Filter Model based on Dual-Objective Optimization
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36287v1 Announce Type: new Abstract: Hospitality service in online marketplaces has become increasingly popular over the past few years, not only because it helps people easily rent short-term lodging but also because it empowers travelers to connect with locals and f…

🅲 hạng C
20
Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36341v1 Announce Type: new Abstract: Early AI programs were often also theories of how people think, and programs that wrote programs were, in part, theories of how people program. Here we report on the reanimation of two such programs that offer two seemingly differe…

🅲 hạng C
20
LoRA on a Budget: Function-Aware Post-Hoc Compression for Adapter Fleets
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36386v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a key mechanism for efficiently specializing foundation models into many task- and user-specific variants. Serving many LoRA adapters under a shared resource budget turns post-hoc compression i…

🅲 hạng C
20
MedConstBench: Benchmarking How Constitutions Steer LLMs in Medical Ethics
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36513v1 Announce Type: new Abstract: As large language models advance rapidly, they are increasingly used to answer medical questions, and many such models are now deployed locally. Once a model is deployed, its behavior is governed mainly by the ethical policy writte…

🅲 hạng C
20
ATEMPO: Amortized Transfer Entropy Model Per-lag Over-Time
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36536v1 Announce Type: new Abstract: When one time series informs another, the delay at which that information arrives determines if models can utilize this relationship effectively. A source may be strongly predictive at one delay but uninformative at neighboring lag…

🅲 hạng C
20
Follow the Herd: A Data-Driven Approach for Actionable Recourse
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.36580v1 Announce Type: new Abstract: As machine learning systems make increasingly greater decisions about people's lives, it is critical to provide users with actionable recourse about how they can achieve their desired outcomes. This problem is currently tackled by …

🅲 hạng C