…View arXiv page View PDF Add to collection Community This paper explores whether compact quantum-inspired recurrent models can efficiently forecast full network traffic matrices under realistic resource constraints. The authors adapt…
…Experimental results highlight the challenges in ESAR , revealing critical bottlenecks in spatial memory, aerial adaptation, and the trade-off between search efficiency and flight safety. We hope ESARBench serves as a valuable…
…estimate how many experts are needed to reach a target loss, decide when to stop adding experts, and trade off scaling the base model versus adding experts under a fixed budget--turning…
…View arXiv page View PDF Add to collection Community Shanghai Jiao Tong University, Sun Yat-sen University, Shanghai Innovation Institute, and OPPO Research Institute unveil LatentSkil, turning agent text skills into plug…
…View arXiv page View PDF GitHub 7 Add to collection Community Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA…
…View arXiv page View PDF GitHub 3 Add to collection Community We’re excited to share our latest work, SciOrch: Learning to Orchestrate Expert LLMs for Frontier Multimodal Scientific Reasoning 🧬 Scientific…
…Newer codecs, like AV1/AVIF, improve the rate-distortion trade-off, but demand far more resources for encoding, impractical without custom ASICs. Recent asymmetric autoencoders deliver high quality under extreme power and…
…View arXiv page View PDF Add to collection Community ENERGYFLOW unifies diffusion-based imitation learning and inverse reinforcement learning by learning a conservative energy field whose gradient drives action generation while exposing…
…View arXiv page View PDF Project page GitHub 71 Add to collection Community SwiftVR is a one-step generative video restoration framework designed for real-time streaming. While recent one-step diffusion…
…View arXiv page View PDF GitHub 13 Add to collection Community Accepted by ICML2026 poster. Accepted by ICML2026. Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but…