Academic
arXiv:2602.21227v1 Announce Type: cross Abstract: As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step …
arXiv:2602.21228v1 Announce Type: cross Abstract: As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing …
arXiv:2602.21231v1 Announce Type: cross Abstract: We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses …
arXiv:2602.21232v1 Announce Type: cross Abstract: Urban vibrancy reflects the dynamic human activity within urban spaces and is often measured using mobile data that captures floating …
arXiv:2602.21233v1 Announce Type: cross Abstract: This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. …
arXiv:2602.21251v1 Announce Type: cross Abstract: Legacy JavaScript systems lack type safety, making maintenance risky. While TypeScript can help, manually adding types is expensive. Previous automated …
arXiv:2602.21255v1 Announce Type: cross Abstract: We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework …
arXiv:2602.21267v1 Announce Type: cross Abstract: Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While …
arXiv:2602.21269v1 Announce Type: cross Abstract: We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of …
arXiv:2602.21327v1 Announce Type: cross Abstract: Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others …
arXiv:2602.21341v1 Announce Type: cross Abstract: Geometry-free view synthesis transformers have recently achieved state-of-the-art performance in Novel View Synthesis (NVS), outperforming traditional approaches that rely on …
arXiv:2602.21346v1 Announce Type: cross Abstract: Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization …
