Proposes DPGNet, leveraging unlabeled fake face data with cross-modal alignment and curriculum pseudo-labeling, boosting detection accuracy by 4.2%.

Zhiqiang Yang, Renshuai Tao, Chunjie Zhang et al.

IROTE uses self-reflective optimization to stably elicit human traits in LLMs, outperforming baselines.

Yuzhuo Bai, Shitong Duan, Muhua Huang et al.

Hi-Vec uses hierarchical layers with dynamic selection and task vectors to improve test-time adaptation, boosting robustness against complex distribution shifts.

Sameer Ambekar, Marta Hasny, Laura Daza et al.

Unigram outperforms BPE in complex morphology languages, especially in Telugu.

Saketh Reddy Vemula, Sandipan Dandapat, Dipti Misra Sharma et al.

This paper systematically evaluates RL techniques in LLM reasoning, revealing that combining group normalization and high clipping surpasses existing strategies.

Zihe Liu, Jiashun Liu, Yancheng He et al.

ReconDreamer-RL integrates diffusion priors for scene reconstruction, reducing collision rate from 0.386 to 0.077 in autonomous driving training.

Chaojun Ni, Guosheng Zhao, Xiaofeng Wang et al.

SwarmVLM integrates VLM and impedance control for heterogeneous robots, achieving 92% success in dynamic warehouse navigation.

Malaika Zafar, Roohan Ahmed Khan, Faryal Batool et al.

LaRender renders object latents with volumetric compositing, reaching 0.767 human-perceived occlusion success on RealOcc.

Xiaohang Zhan, Dingming Liu

Proposes SOFA, a deep learning framework that simulates post-ablation scars, predicts AF recurrence risk, and optimizes procedural parameters, reducing predicted risk by 22.18%.

Yunsung Chung, Chanho Lim, Ghassan Bidaoui et al.

D3P: A reinforcement learning-based adaptive diffusion policy accelerates robotic inference by 2.2× without performance loss, through dynamic denoising step allocation.

Shu-Ang Yu, Feng Gao, Yi Wu et al.

Restage4D leverages single video and motion priors to achieve physically consistent 4D deformable scene reconstruction with geometric correction.

Jixuan He, Chieh Hubert Lin, Lu Qi et al.

GLM-4.5 uses deep MoE architecture with 355B parameters, integrating thinking and response modes, achieving top ARC benchmark results.

GLM-4. 5 Team, :, Aohan Zeng et al.

Memp enhances agent procedural memory by distilling past trajectories, showing a 50% success rate improvement.

Runnan Fang, Yuan Liang, Xiaobin Wang et al.

S-Path exploits hierarchical 3D scene graphs with semantic path decomposition, achieving 6× faster planning while maintaining path optimality.

Saad Ejaz, Marco Giberna, Muhammad Shaheer et al.

GenD fine-tunes only LayerNorm parameters, achieving state-of-the-art cross-dataset AUROC in deepfake detection, surpassing complex models.

Andrii Yermakov, Jan Cech, Jiri Matas et al.

AURA employs a multi-layered Process Reward Model to enhance logical coherence and safety in LLM reasoning, reducing risks by 20-50%.

Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee et al.

HOLODECK 2.0 integrates vision-language models with 3D generative models for diverse, styled scene creation and interactive editing.

Zixuan Bian, Ruohan Ren, Yue Yang et al.

Introduces KuaiLive, a large-scale, real-time, multi-behavior dataset from Kuaishou for live streaming recommendation, supporting multi-task learning.

Changle Qu, Sunhao Dai, Ke Guo et al.

Proposes a taxonomy for unsupervised VLM adaptation based on unlabeled data availability, covering four paradigms, improving generalization.

Hao Dong, Lijun Sheng, Jian Liang et al.

Introduces RTI-inspired scheme for diffusion policy inference, reducing runtime by over 85% while maintaining performance.

Yufei Duan, Hang Yin, Danica Kragic