YUBI: Efficient data collection for bimanual manipulation, 8434 hours, improves operational efficiency.

Takehiko Ohkawa, Jumpei Arima, Yuki Noguchi et al.

Proposed a continuous-time Markov chain framework to enhance insertion language models' flexibility and sampling efficiency.

Dhruvesh Patel, Benjamin Rozonoyer, Soumitra Das et al.

iSAGE framework achieves remote sensing semantic segmentation via sparse point supervision, recovering 97.2% of dense supervision performance.

Osmar Luiz Ferreira de Carvalho, Osmar Abilio de Carvalho Junior, Anesmar Olino de Albuquerque et al.

Using GLOW normalizing flows and stochastic interpolants, the study evaluates neural models' posterior reliability in high-dimensional cosmic initial condition inference.

Ludvig Doeser, Jens Jasche

MemoryVLA++ integrates memory and imagination for full temporal modeling, significantly improving robotic task success rates.

Hao Shi, Weiye Li, Bin Xie et al.

DRPO introduces smooth advantage-weighted quadratic regularization to improve stability and efficiency in LLM RL training, replacing hard masks with continuous gradient weights.

Jiarui Yao, Xiangxin Zhou, Penghui Qi et al.

iMaC translates future robot actions into image controls, significantly improving spatial accuracy in video prediction and policy evaluation.

Zhenyu Wu, Xiuwei Xu, Yukun Zhou et al.

Introducing Topological Neural Operators (TNO), a framework leveraging cell complexes and discrete exterior calculus to improve PDE modeling on complex geometries, achieving over 20% accuracy gains.

Lennart Bastian, Samuel Leventhal, Mustafa Hajij et al.

FASE employs graph-based semantic embeddings to approximate code correctness, achieving 25% higher correlation and only 0.3% of traditional computational cost.

Shizhe Lin, Ladan Tahvildari

POTATR is a lightweight 29M-parameter image-to-graph model that significantly improves page-level table extraction accuracy and efficiency.

Brandon Smock, Libin Liang, Max Sokolov et al.

Proposes an fully automated time-series forecasting framework combining high-frequency dataset TimeTrack with dynamic local telemetry, using NAS to generate accurate models, effectively addressing cold-start issues.

Abd Elghani Meliani, Arora Sagar, Adlen Ksentini et al.

Combines Quality Diversity (QD) algorithms with supervised discriminative models, using multi-frequency CPPNs and MAP-Elites to explore diverse audio solutions with high novelty and quality.

Björn Þór Jónsson, Çağrı Erdem, Stefano Fasciani et al.

Intervention-aware variational quantum predictive control (IA-VQC-DPC) significantly reduces safety violations and reliance on safety layers in building control, validated via safety attribution protocols.

Yifan Wang

DARP introduces difference-aware retrieval policies, leveraging local neighborhood structures to improve imitation learning robustness, achieving 15-46% performance gains over standard behavior cloning.

Quinn Pfeifer, Ethan Pronovost, Paarth Shah et al.

This paper reveals that RLHF achieves shallow alignment by compressing partisan signals without removing the underlying partisan structure, as shown through internal representation analysis of Llama 3.1 8B.

Wendy K. Tam

AdvGRPO framework combines dense multi-channel rewards and advantage decoupling for joint attacker-defender training, achieving over 90% attack success rate and superior defense robustness.

Blake Bullwinkel, Eugenia Kim, Amanda Minnich et al.

Proposes a logic-guided data extraction framework combining ASP and LLMs, reducing calls by 40% while maintaining accuracy.

Mario Alviano, Lorenzo Grillo, Nicola Leone et al.

Muon optimizer outperforms Adam in robustness and transferability, with larger logit margins and higher spectral rank in features.

Tianyu Ruan, Fengzhuo Zhang, Shuche Wang et al.

DexPIE improves dexterous manipulation policies using real-world experience, achieving a 37% success rate increase.

Ruizhe Liao, Wenrui Chen, Liangji Zeng et al.

Popcorn benchmark combines title-aligned full-movie/trailer embeddings with VLM-encoded thumbnails to evaluate visual evidence in multimodal movie recommendation.

Ali Tourani, Fatemeh Nazary, Yashar Deldjoo et al.