Stay updated with the latest research and technology news
arXiv:2601.21346v1 Announce Type: new Abstract: Parameter tuning is a powerful approach to enhance adaptability in model predictive control (MPC) motion planners. However, existing methods typically...
arXiv:2601.21348v1 Announce Type: new Abstract: Controlling memorization in diffusion models is critical for applications that require generated data to closely match the training distribution. Existing...
arXiv:2601.21349v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small subset of experts, where the router plays a central...
arXiv:2601.21350v1 Announce Type: new Abstract: A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback....
arXiv:2601.21351v1 Announce Type: new Abstract: Attention-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN...
arXiv:2601.21352v1 Announce Type: new Abstract: GUI agents are designed to automate repetitive tasks and enhance productivity. However, existing GUI agents struggle to recover once they...
arXiv:2601.21353v1 Announce Type: new Abstract: Recent years have seen significant advances in using formal verification to check hardware security properties. Of particular practical interest are...
arXiv:2601.21357v1 Announce Type: new Abstract: Bayesian Optimization (BO) is a principled approach for optimizing expensive black-box functions, with Expected Improvement (EI) being one of the...
arXiv:2601.21358v1 Announce Type: new Abstract: Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning...
arXiv:2601.21359v1 Announce Type: new Abstract: Failures in complex systems demand rapid Root Cause Analysis (RCA) to prevent cascading damage. Existing RCA methods that operate without...
arXiv:2601.21360v1 Announce Type: new Abstract: The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability...
arXiv:2601.21362v1 Announce Type: new Abstract: Edge-assisted mobile video analytics (MVA) applications are increasingly shifting from using vision models based on convolutional neural networks (CNNs) to...
arXiv:2601.21363v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust...
arXiv:2601.21365v1 Announce Type: new Abstract: Artificial intelligence (AI) systems are revolutionizing fields such as medicine, drug discovery, and materials science; however, many technologists and policymakers...
arXiv:2601.21366v1 Announce Type: new Abstract: The forward pass of a Transformer can be seen as an interacting particle system on the unit sphere: time plays...
arXiv:2601.21367v1 Announce Type: new Abstract: Backpropagation algorithm has driven the remarkable success of deep neural networks, but its lack of biological plausibility and high computational...
arXiv:2601.21368v1 Announce Type: new Abstract: This paper develops a unified theory of natural superconvergence points for polynomial spline approximations to second-order elliptic problems. Beginning with...
arXiv:2601.21369v1 Announce Type: new Abstract: Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to...
arXiv:2601.21371v1 Announce Type: new Abstract: The growing prevalence of extreme weather events driven by climate change poses significant challenges to power system resilience. Infrastructure damage...
arXiv:2601.21372v1 Announce Type: new Abstract: In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization...
arXiv:2601.21375v1 Announce Type: new Abstract: Large language models (LLMs) show promise as teaching assistants, yet their teaching capability remains insufficiently evaluated. Existing benchmarks mainly focus...
arXiv:2601.21376v1 Announce Type: new Abstract: Existing video-based 3D Human Mesh Recovery (HMR) methods often produce physically implausible results, stemming from their reliance on flawed intermediate...
arXiv:2601.21379v1 Announce Type: new Abstract: AI-assisted programming tools are widely adopted, yet their practical utility is often undermined by undesired suggestions that interrupt developer workflows...
arXiv:2601.21380v1 Announce Type: new Abstract: Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning...