This paper introduces TxFM, a masked autoencoder trained on 1.4 million RNA-seq samples, outperforming large-scale foundation models in gene representation learning.

Kian Kenyon-Dean, Alina Selega, Ihab Bendidi et al.

Proposes Functional Attention, transforming pointwise attention into linear operators in function spaces, achieving resolution-invariant PDE solving and 3D segmentation with superior performance.

Jiefang Xiao, Maolin Gao, Simon Weber et al.

Study finds CLIP's concept binding is complex; new models use multiplicative interactions for low-complexity binding.

Arnas Uselis, Darina Koishigarina, Seong Joon Oh

Proposed horizon-control strategies—Progressive OPD and Truncated OPD—significantly improve long-horizon on-policy distillation efficiency, achieving 3× faster training and comparable performance with only 10% rollout length.

Yaocheng Zhang, Jiajun Chai, Yuqian Fu et al.

Pure tactile-based deep RL enables multi-finger robot to control small object separation with success rates close to 94%, validated in real-world transfer.

Ulf Kasolowsky, Berthold Bäuml

BenHalluEval evaluates Bengali LLM hallucinations; BenHalluScore ranges from 7.72% to 55.42%.

Shefayat E Shams Adib, Ahmed Alfey Sani, Ekramul Alam Esham et al.

IDOL employs inverse dynamics to decode future scene transitions into motion features, significantly improving autonomous driving trajectory planning.

Chenghao Zhang, Timin Li, Dongmei Li

VolFill employs a latent diffusion model with TUDF grids to reconstruct complete 3D scenes from a single RGB image, achieving state-of-the-art accuracy.

Tuan Duc Ngo, Chuang Gan, Evangelos Kalogerakis

REIS combines lightweight scene gating and KV-guided inference, significantly reducing robotic reasoning redundancy for real-time decision-making.

Joonhee Lee, Hyunseung Shin, Hyunmi Kim et al.

Proposes an adaptive control framework combining artificial time delay estimation with barrier Lyapunov functions for Euler-Lagrange robots, effectively handling state-dependent uncertainties and time-varying constraints.

Saksham Gupta, Rishabh Dev Yadav, Sarthak Mishra et al.

Proposed a constrained max-min MORL framework using convex optimization, validated convergence and practical effectiveness across multiple domains.

Giseung Park, Hyunyoung Nam, Woohyeon Byeon et al.

This study introduces a multi-turn multi-agent dialogue framework to evaluate VLMs in spatial reasoning, showing limited improvements mainly due to visual grounding challenges.

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

Memristor-based analog SNN accelerator reduces energy consumption by 12.7× and delay by 1.26×, enabling real-time edge intelligence for bio-inspired interception tasks.

Qianhou Qu, Sheng Lu, Liuting Shang et al.

This paper establishes the theoretical foundation for linear recurrent memory units (ALF) in partially observable reinforcement learning, constructing two linear filters that precisely replicate belief dynamics.

Yike Zhao, Onno Eberhard, Malek Khammassi et al.

Introducing Fixed-Point Masked Generative Models (FP-MGMs), which use shared attention layers with a fixed-point solver for adaptive depth, reducing parameters by 38.8% and training time by 11.5%.

Andrea Miele, Yiming Qin, Alba Carballo-Castro et al.

HyBIRD uses hyperbolic bridge retrieval for methodology inspiration, achieving 59.034 mAP.

Yang Yang, Boyun Xu, Hao Fu et al.

Introduces Neural Token Reconstruction (NTR) with masked latent reconstruction to enhance scene token representations, achieving 8.0461 RFS on Waymo E2E.

Jiahui Li, Jiawei Sun, Zixiang Ren et al.

Model-agnostic signal discovery method using machine learning enhances exploration of new phenomena.

Oz Amram, Marco Letizia, Mikael Kuusela

iVGR internalizes visual localization into textual reasoning using reinforcement learning, significantly enhancing MLLMs' performance.

Chang-Bin Zhang, Yujie Zhong, Qiang Zhang et al.

Introduced RHELM benchmark with multi-source heterogeneous data and dynamic user profiles to evaluate long-term memory in dialogue models.

Han Zhang, Zihao Tang, Xin Yu et al.