Proposed Sol Video Inference Engine uses five techniques—cache, sparse attention, token pruning, quantization, kernel fusion—for 2× acceleration of video diffusion models.

Yitong Li, Junsong Chen, Haopeng Li et al.

Multi4D employs multi-level competitive allocation for high-fidelity dynamic Gaussian splatting, balancing motion consistency and detail preservation.

Rui Wang, Quentin Lohmeyer, Siyu Tang et al.

Wh0 framework uses generative video world models to create a 50k human-hand manipulation dataset, boosting VLA model zero-shot success to 38.9%.

Yangtao Chen, Zixuan Chen, Peiyang Wang et al.

SPRINT mitigates popularity bias amplification in scaling Transformer-based recommenders, improving accuracy and fairness.

Weiqin Yang, Yue Pan, Chongming Gao et al.

Confident Layer Decoding dynamically selects the most reliable near-final layer to enhance reasoning in large language models.

Xuanming Zhang, Sining Zhoubian, Yuxuan Chen et al.

CRAwLeR uses legal cross-references for context-aware chunk retrieval, achieving Recall@10 of 55%.

Maciej Jalocha, William Michelsen

UnityShots employs dual-slot memory and boundary-aware gating in LTX-2.3 to generate coherent multi-shot audio-video sequences, outperforming baselines on cross-shot consistency.

Jiehui Huang, Yuechen Zhang, Bin Xia et al.

DVDrive introduces divided-view perception with Transformer, improving instruction-conditioned trajectory prediction, reducing ADE from 0.372 to 0.358.

Zijian Fu, Xiangyang Chu, Mengshi Qi et al.

Replace MLP with Radial Basis Function Networks to enhance representation quality in self-supervised learning.

Andreas Schliebitz, Heiko Tapken, Martin Atzmueller

Proposes GRPO with JS divergence to balance performance and diversity in LlamaGen and Janus-7B.

Yuanhao Chiang, Hongbo Duan, Chunru Yang et al.

TreeProp enables model-parallel deep learning with tree structures, achieving O(log N) time complexity.

Neeraj Mohan Sushma, Aditya Nagarsekar, Cabrel Teguemne Fokam et al.

FLM-Occ enhances indoor occupancy prediction efficiency via feed-forward likelihood maximization, achieving 3.7x speedup with only 32 superquadrics.

Guangcheng Chen, Lihuang Fang, Huaqi Tao et al.

Proposes an objective-behavior alignment diagnostic workflow using behavior space analysis to reveal hidden behavioral differences in MORL.

Antonio Mone, Zuzanna Osika, Florian Felten et al.

Answer Engineering uses local trajectory editing to improve protocol compliance in LLMs, boosting SSNHL compliance from 25.1% to 83.5%.

Victor Lavrenko, Anastasiia Molodnitskaia

Probing LLM preferences via parametric variation reveals significant incoherence.

Elena Ajayi, Angelica Chowdhury, Seth Lazar

Hierarchical Transformer detects multi-turn jailbreaks with 0.9394 F1, outperforming baselines.

Chenhui Hu, Muhammed Salih, Sudipto Guha et al.

Proposes a block-level heterogeneous CPU-GPU inference framework with cross-frame asynchronous pipeline, reducing latency by over 20% on VLA models.

Haibo HU, Lianming Huang, Qiao Li et al.

DUET leverages human demonstration pretraining with Action Chunking Transformer to enhance heterogeneous dual-robot collaboration, achieving 20% higher success rates.

Yiqi Zhao, Ruohai Ge, Celina Shiyu Wang et al.

Proposed ViGiL3D++ combines scene graph sampling and LLM rephrasing to generate diverse 3D grounding descriptions, improving dataset richness.

Austin T. Wang, Dongchen Yang, Angel X. Chang

LPM uses dynamic soft prompts for personalization, improving accuracy by 8.8% on PersonaMem v1, reducing KV-cache by 64x.

Debrup Das, Avinash Amballa, Yashas Malur Saidutta et al.