Proposes a verified safe reinforcement learning framework combining curriculum learning, incremental verification, and multi-controller strategies, extending safety horizon by 10x.

Junlin Wu, Huan Zhang, Yevgeniy Vorobeychik

MuDreamer predicts rewards, value, and actions in latent space without pixel reconstruction, boosting robustness and training speed.

Maxime Burchi, Radu Timofte

CraftsMan3D employs a 3D native diffusion model and interactive refinement to generate high-fidelity meshes within seconds.

Weiyu Li, Jiarui Liu, Hongyu Yan et al.

AnalogCoder uses training-free LLMs to generate Python code for automatic analog circuit design, achieving over 83% success on 24 tasks.

Yao Lai, Sungyoung Lee, Guojin Chen et al.

This paper analyzes spectral regularization algorithms for vector-valued learning, confirming the saturation effect of ridge regression and establishing optimal upper bounds.

Dimitri Meunier, Zikai Shen, Mattes Mollenhauer et al.

RepNoise employs layer-wise noise injection and mutual information minimization to resist harmful fine-tuning, preserving model capabilities.

Domenic Rosati, Jan Wehner, Kai Williams et al.

LucidPPN enhances user understanding in computer vision by separating color from other visual features.

Mateusz Pach, Dawid Rymarczyk, Koryna Lewandowska et al.

Introduces parametric WKM to enhance LLM-based agent planning, reducing trial-and-error and hallucinations, achieving superior results on complex tasks.

Shuofei Qiao, Runnan Fang, Ningyu Zhang et al.

Proposes a membership-query-based active learning framework for solving 0-1 integer programs with unknown knapsack constraints, improving query efficiency and solution quality.

Rosario Messana, Rui Chen, Andrea Lodi et al.

ChatScene employs LLMs and knowledge retrieval to generate safety-critical traffic scenarios, enhancing autonomous vehicle testing.

Jiawei Zhang, Chejian Xu, Bo Li

Proposes nondeterministic structural causal models (NSCM) using multi-valued functions to enhance counterfactual semantics.

Sander Beckers

Proposes diffusion-based learning of multi-layer latent energy-based priors, improving sampling and hierarchical representation in generative models.

Jiali Cui, Tian Han

Proposes FRPN guidance and IMM filtering for fast, accurate UAV mid-air interception, reducing response time by 20% and increasing success rate to 85%.

Michal Pliska, Matouš Vrba, Tomáš Báča et al.

Cross-Layer Attention (CLA) shares KV heads between adjacent layers, reducing cache size by 2× with minimal accuracy loss.

William Brandon, Mayank Mishra, Aniruddha Nrusimha et al.

Introduces an energy-based kernel framework for spectral learning of unbounded diffusion generators, providing dimension-free bounds and avoiding spurious eigenvalues.

Vladimir R. Kostic, Karim Lounici, Helene Halconruy et al.

DIAMOND employs a diffusion-based world model achieving 1.46 human-normalized score on Atari 100k, surpassing previous methods.

Eloi Alonso, Adam Jelley, Vincent Micheli et al.

xFinder optimizes key answer extraction in LLM evaluation, achieving 93.42% extraction accuracy.

Qingchen Yu, Zifan Zheng, Shichao Song et al.

FIFO-Diffusion leverages pretrained diffusion models with diagonal denoising, latent partitioning, and lookahead to generate infinite long videos without extra training.

Jihwan Kim, Junoh Kang, Jinyoung Choi et al.

Proposes a resilient planning model based on FA-MDP, incorporating actuator failure probabilities, to optimize robot fault response strategies.

Kyle Baldes, Diptanil Chaudhuri, Jason M. O'Kane et al.

Integrating point clouds and NeRF with LLMs enhances 3D scene understanding and reasoning.

Xianzheng Ma, Brandon Smart, Yash Bhalgat et al.