GenEvolve achieves self-evolving image generation via tool-orchestrated visual experience distillation, enhancing generation quality.

Sixiang Chen, Zhaohu Xing, Tian Ye et al.

Insights Generator enhances LLM diagnostics with a multi-agent system, improving performance by 30.4pp.

Akshay Manglik, Apaar Shanker, Kaustubh Deshpande et al.

Proposed a structural latent point learning method, achieving a 56% task success rate on RLBench.

Yicheng Jiang, Jiaxu Wang, Junhao He et al.

FTerViT fully ternarizes all weights and normalization parameters, achieving 82.43% accuracy with 15× compression on ImageNet.

Szymon Ruciński, Pietro Bonazzi, Engin Türetken et al.

ROAR-3D employs a token-wise view router to upgrade pretrained single-view models for multi-view 3D generation, achieving state-of-the-art results.

Hanxiao Sun, Mingxin Yang, Shuhui Yang et al.

Introduces Musical Attention mechanism to improve music generation quality, reducing repetition and enhancing diversity.

Shinnosuke Takasuka, Hideo Mukai

Transforming driving VLA into an inverse kinematics framework with future visual prediction and diffusion-based IK network, achieving performance comparable to much larger models.

Junsung Park, Hyunjung Shim

CHOIR uses contact-aware spatial rectification and joint optimization for monocular 4D HOI reconstruction; the supplied text reports no numerical metrics.

Hao Xu, Yilin Liu, Yinqiao Wang et al.

PEACH framework uses point cloud encoding for zero-shot transfer in material-conditioned graph network simulators.

Philipp Dahlinger, Balázs Gyenes, Niklas Freymuth et al.

PlexRL employs cluster-level scheduling to multiplex large language models across RLVR tasks, reducing GPU cost by 37.58%.

Yiqi Zhang, Fangzheng Jiao, Tian Tang et al.

DUET framework leverages linear decodability of emotion in hidden states, combining hidden space bias and mel-space gradient guidance for controllable emotional TTS without retraining.

Xu Zhang, Longbing Cao, Zhangkai Wu

GAMR actively synthesizes virtual outliers and uses geometric regularization to improve robustness against noisy labels, outperforming SOTA on CIFAR datasets with 80% asymmetric noise.

Ningkang Peng, Jingyang Mao, Xiaoqian Peng et al.

NeuroNL2LTL unifies neural translation with formal verification, achieving 28% semantic equivalence and 86% satisfiable formulas on 200,000+ requirements.

Paapa Kwesi Quansah, Ernest Bonnah

Auto-Dreamer employs offline memory consolidation via region rewriting, achieving 7% higher success and 12× smaller memory on ScienceWorld.

Chongrui Ye, Yuxiang Liu, Yu Wang et al.

HeadKV achieves efficient autoregressive image generation by asymmetric cache allocation across attention heads, significantly improving memory efficiency.

Guotao Liang, Baoquan Zhang, Zhiyuan Wen et al.

$Δ$YNAMICS uses language to infer rigid-body dynamics from videos, achieving 7x improvement in segmentation IoU.

Chia-Hsiang Kao, Cong Phuoc Huynh, Chien-Yi Wang et al.

Introduces SpectralUCB and SpectralTS algorithms leveraging spectral features and effective dimension to efficiently learn smooth graph functions in large-scale bandit problems, achieving low regret.

Tomáš Kocák, Michal Valko, Rémi Munos et al.

SUGAR leverages human videos to learn humanoid loco-manipulation skills without task rewards or reference motions, enabling zero-shot transfer.

Tianshu Wu, Xiangqi Kong, Yue Chen et al.

Proposes the multi-class unhinged loss as the unique convex symmetric loss, improving robustness to noisy labels.

Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère

MetaEarth-MM enables unified generation and translation of remote sensing images across five modalities with scene-centered joint modeling.

Zhiping Yu, Chenyang Liu, Jinqi Cao et al.