Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2606. 10286v1 Announce Type: new Abstract: Open-pit mine scheduling is a critical process for maximizing economic return under complex geotechnical and operational constraints.
arXiv:2604. 24668v3 Announce Type: replace Abstract: Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems.
arXiv:2606. 10944v1 Announce Type: new Abstract: We introduce a new tool, Express, for converting a non-causal attention approximation into a causal approximation with matching approximation guarantees.
arXiv:2606. 10942v1 Announce Type: cross Abstract: As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust.
arXiv:2606. 10862v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, but most evaluations assume that task-relevant objects are fully visible.
arXiv:2512. 08280v3 Announce Type: replace-cross Abstract: Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control.
arXiv:2606. 11119v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.
arXiv:2606. 10528v1 Announce Type: new Abstract: Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM).
arXiv:2606. 11033v1 Announce Type: cross Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation.
arXiv:2505. 23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization with genuine reasoning.
arXiv:2606. 10393v1 Announce Type: new Abstract: Credit-card fraud detection is difficult because fraudulent transactions are rare, costly, and unevenly distributed.
arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.
arXiv:2606. 10092v1 Announce Type: new Abstract: Decision-making under risk is typically studied through single-shot lottery choices.
arXiv:2606. 10329v1 Announce Type: cross Abstract: As one of the most destructive natural disasters, earthquakes have struck many countries around the world in recent years, causing serious economic losses.
arXiv:2606. 11017v1 Announce Type: new Abstract: Airport surface operations increasingly constrain performance at high-throughput hubs.
arXiv:2606. 10975v1 Announce Type: new Abstract: Finding convenient spaces in which certain hypotheses regarding an assumed sparse structure of natural signals hold true has become a desirable result in recent research, its implications being reflected in areas such as data compression, noise reduction and feature extraction.
arXiv:2510. 04195v2 Announce Type: replace Abstract: Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries by providing shortest paths.
arXiv:2606. 09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive data while preserving model performance.
arXiv:2606. 11042v1 Announce Type: new Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks.
arXiv:2606. 10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains.