Stay updated with the latest research and technology news
arXiv:2602.24096v2 Announce Type: replace Abstract: Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as...
arXiv:2602.24290v2 Announce Type: replace Abstract: Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented,...
arXiv:2603.00152v2 Announce Type: replace Abstract: Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to...
arXiv:2603.00395v2 Announce Type: replace Abstract: Hearables are becoming ubiquitous, yet their sound controls remain blunt: users can either enable global noise suppression or focus on...
arXiv:2603.00918v2 Announce Type: replace Abstract: Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models is a promising path...
arXiv:2603.01007v3 Announce Type: replace Abstract: 3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing...
arXiv:2603.01145v2 Announce Type: replace Abstract: In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or...
arXiv:2603.01209v2 Announce Type: replace Abstract: Tool-augmented LLMs are increasingly deployed as agents that interleave natural-language reasoning with executable Python actions, as in CodeAct-style frameworks. In...
arXiv:2603.01223v2 Announce Type: replace Abstract: Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct...
arXiv:2603.01620v3 Announce Type: replace Abstract: Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment...
arXiv:2603.01776v2 Announce Type: replace Abstract: Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models (LLMs). While emerging transformation-based methods...
arXiv:2603.01919v2 Announce Type: replace Abstract: Access to frontier large language models (LLMs), such as GPT-5 and Gemini-2.5, is often hindered by high pricing, payment barriers,...
arXiv:2603.01972v2 Announce Type: replace Abstract: Modern societal challenges, such as climate change, urbanization, and water resource management, demand integrated, multi-discipline, multi-problem approaches to frame and...
arXiv:2603.02002v2 Announce Type: replace Abstract: Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical...
arXiv:2603.02175v2 Announce Type: replace Abstract: Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is...
arXiv:2603.02573v2 Announce Type: replace Abstract: Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of...
arXiv:2603.02727v2 Announce Type: replace Abstract: Medical image segmentation requires models that preserve fine anatomical boundaries while remaining efficient for clinical deployment. While transformers capture long-range...
arXiv:2603.02743v3 Announce Type: replace Abstract: Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and often...
arXiv:2603.03043v2 Announce Type: replace Abstract: While formal robustness verification has seen significant success in image classification, scaling these guarantees to object detection remains notoriously difficult...
arXiv:2603.03056v2 Announce Type: replace Abstract: Neighborhood graphs are a critical but often fragile step in spectral clustering of text embeddings. On realistic text datasets, standard...
arXiv:2603.03065v2 Announce Type: replace Abstract: Dense retrieval services increasingly underpin semantic search, recommendation, and retrieval-augmented generation, yet clients typically receive only a top-$k$ list with...
arXiv:2603.03201v2 Announce Type: replace Abstract: Reasoning is the ability to integrate internal states and external inputs in a meaningful and semantically consistent flow. Contemporary machine...
arXiv:2603.03229v2 Announce Type: replace Abstract: The shock response spectrum (SRS) is widely used to characterize the response of single-degree-of-freedom (SDOF) systems to transient accelerations. Because...
arXiv:2603.03378v2 Announce Type: replace Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment...