Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
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:2606. 10229v1 Announce Type: cross Abstract: We study whether demonstration-curation metrics that detect defective training episodes also improve the downstream behavior-cloning policy that trains on the curated data.
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. 10092v1 Announce Type: new Abstract: Decision-making under risk is typically studied through single-shot lottery choices.
arXiv:2606. 09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped.
arXiv:2606. 09909v1 Announce Type: cross Abstract: With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strategy to prevent malicious content forgery in personalized image generation.
arXiv:2606. 09882v1 Announce Type: cross Abstract: The paradigm of digital twin cities is shifting from coarse visual mapping toward more precise and actionable digitization of urban assets.
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
arXiv:2606. 09873v1 Announce Type: cross Abstract: Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer.
arXiv:2606. 10089v1 Announce Type: cross Abstract: In this work, we develop theoretical foundation for flow matching with neural-network-parameterized conditional velocity fields.
arXiv:2606. 09923v1 Announce Type: cross Abstract: Neural operators such as the Fourier Neural Operator (FNO) have emerged as powerful surrogates for solving partial differential equations (PDEs), achieving speedups of several orders of magnitude over traditional numerical solvers.
arXiv:2605. 27914v2 Announce Type: replace-cross Abstract: Benchmarking is mature where answers are verifiable -- math, code, reasoning -- but the fastest-growing uses of LLMs are subjective and human-facing: companionship, emotional support, counseling.
arXiv:2606. 09874v1 Announce Type: new Abstract: Reconstruction-based methods are widely used for time series anomaly detection, where models are trained to reconstruct subsequences, and anomalies are identified through reconstruction errors.
arXiv:2606. 10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence.
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. 09887v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness.
arXiv:2603. 22017v2 Announce Type: replace Abstract: This work presents a collection of multi-modal domain adapted large language models built upon the instruction tuned variants of open weight models (Gemma 3, Qwen 3, Gemma 4) using a relatively small dataset of around 50 million tokens.