GraspQP optimizes diverse, stable dexterous grasps using differentiable force closure, enhancing grasp diversity and stability.

René Zurbrügg, Andrei Cramariuc, Marco Hutter

Integrating LSTM, DeepVAR, and GPVAR models for dynamic covariance forecasting, improving portfolio risk estimation.

Maciej Wysocki, Paweł Sakowski

MeshCoder employs multimodal LLMs to convert point clouds into editable Blender Python scripts, enabling detailed 3D shape reconstruction with over 86% IoU and 0.027 Chamfer Distance.

Bingquan Dai, Li Ray Luo, Qihong Tang et al.

Lossless compression using Huffman coding achieves up to 83% compression for FP8 and BF16 formats.

Anat Heilper, Doron Singer

Proposed an integrated path planning framework with spatiotemporal prediction, improving target tracking accuracy by 25% in dynamic environments.

Sanjeev Ramkumar Sudha, Marija Popović, Erlend M. Coates

Nearly lossless ANN-to-SNN conversion at the first timestep via Polarity Multi-Spike Mapping, achieving high accuracy.

Hangming Zhang, Zheng Li, Chenxiang Ma et al.

GeoSAM2 achieves 84.06% mIoU on PartObjaverse-Tiny and 74.42% on PartNetE using multi-view 2D mask prediction for 3D segmentation.

Ken Deng, Yunhan Yang, Jingxiang Sun et al.

Proposes PING, an automatic prefix injection method, to enhance LLM safety in agentic tasks while maintaining performance.

Dongyoon Hahm, Taywon Min, Woogyeol Jin et al.

PhysGM predicts 3D Gaussian and physical parameters from a single image, enabling real-time 4D scene synthesis in under one minute.

Chunji Lv, Zequn Chen, Donglin Di et al.

MAVIS achieves multi-objective alignment via inference-time value-guided selection, enhancing Pareto front performance.

Jeremy Carleton, Debajoy Mukherjee, Srinivas Shakkottai et al.

HiFo-Prompt integrates Foresight and Hindsight mechanisms, significantly enhancing LLM-driven heuristic design with superior quality, faster convergence, and higher query efficiency.

Chentong Chen, Mengyuan Zhong, Ye Fan et al.

EgoTwin uses a diffusion transformer to generate consistent first-person video and human motion.

Jingqiao Xiu, Fangzhou Hong, Yicong Li et al.

Contact surface representation enabling closed-form proximity computation accelerates whole-body manipulation planning by 77%.

Victor Levé, João Moura, Sachiya Fujita et al.

DyCrowd framework achieves spatio-temporal consistent 3D reconstruction of dynamic crowds from large-scene videos.

Hao Wen, Hongbo Kang, Jian Ma et al.

Trust-region constrained measure transport improves high-dimensional stochastic control, reducing control error to 0.002 and transfer path RMSD to 1.2 Å, outperforming baselines.

Denis Blessing, Julius Berner, Lorenz Richter et al.

TiP4GEN employs a dual-branch diffusion framework with 3D Gaussian Splatting for high-quality dynamic panoramic 4D scene synthesis.

Ke Xing, Hanwen Liang, Dejia Xu et al.

EgoLoc employs hand 3D dynamics and vision-language models for zero-shot temporal interaction localization, precisely identifying contact and separation moments.

Junyi Ma, Erhang Zhang, Yin-Dong Zheng et al.

FineCE is a supervised fine-grained confidence estimation method that significantly improves early and continuous confidence prediction during text generation.

Jinyi Han, Tingyun Li, Shisong Chen et al.

Introduced AF-CoT-Train dataset and AF-Reasoning-Eval benchmark, significantly enhancing reasoning in audio language models.

Zhifeng Kong, Arushi Goel, Joao Felipe Santos et al.

Thyme integrates code-driven image operations and reasoning, boosting multimodal model performance.

Yi-Fan Zhang, Xingyu Lu, Shukang Yin et al.