DaMo employs neural networks to predict optimal data mixing ratios in multimodal LLM fine-tuning, achieving 3.38% performance gain on PhoneAgentBench.

Kai Shi, Jun Yang, Ni Yang et al.

Using NeRFs and 3DGS for 4D representation generation and reconstruction, enhancing dynamic scene understanding.

Mingrui Zhao, Sauradip Nag, Kai Wang et al.

Integrating VLM with webpage screenshots and HTML improves online shopper behavior prediction accuracy by over 6%, enhancing realism in multi-modal models.

Yimeng Zhang, Jiri Gesi, Ran Xue et al.

LightMem mimics human memory, organizing info into three stages, boosting long-term reasoning with 7.7% accuracy gain and 38× token reduction.

Jizhan Fang, Xinle Deng, Haoming Xu et al.

Proposes Search Self-play (SSP), a self-supervised method that co-evolves question proposing and answering models via multi-turn search and retrieval verification, outperforming baselines.

Hongliang Lu, Yuhang Wen, Pengyu Cheng et al.

Proposes probabilistic risk metrics for quantifying attack impact and resources in NCS, enhancing resilience assessment.

Sribalaji C. Anand, Anh Tung Nguyen, André M. H. Teixeira et al.

PROSPER framework leverages LLMs with residual networks and coarse-to-fine sparsification, achieving 10.2% recall gain in product search.

Hongru Song, Yu-an Liu, Ruqing Zhang et al.

COPPOL integrates conformal prediction into semantic segmentation, achieving over 6× hazard coverage and 50% fewer violations in risk-aware RL navigation.

Daniel Bethell, Simos Gerasimou, Radu Calinescu et al.

VFM-VAE leverages frozen VFM as encoder with novel decoder, achieving gFID 1.62 in 640 epochs, 10× faster than prior methods.

Tianci Bi, Xiaoyi Zhang, Yan Lu et al.

MAGDrop enhances DNN generalization with momentum-adaptive dropout, achieving 99.52% on MNIST.

Adeel Safder

Glyph renders long texts into images processed by VLMs, achieving 3-4× token compression with performance comparable to Qwen3-8B.

Jiale Cheng, Yusen Liu, Xinyu Zhang et al.

Proposes Enterprise Deep Research (EDR), a multi-agent framework achieving state-of-the-art enterprise analytics with superior performance metrics.

Akshara Prabhakar, Roshan Ram, Zixiang Chen et al.

FARE uses iterative rejection sampling SFT to outperform 70B+ evaluators in reasoning domains.

Austin Xu, Xuan-Phi Nguyen, Yilun Zhou et al.

Repeated LLM sampling with Eudoxia verification improved simulated FaaS throughput by up to 371.1% over FIFO.

Jacopo Tagliabue

Proposes a context-aware pseudo-label scoring framework for zero-shot video summarization, achieving 57.58 F1 on SumMe.

Yuanli Wu, Long Zhang, Yue Du et al.

LLM-driven industry agents automate complex tasks, enhancing productivity.

Yihong Tang, Kehai Chen, Liang Yue et al.

ISE combines online embedding refinement and failed-plan rejection to improve video replanning on five Meta-World tasks with 400 trials each.

Po-Chen Ko, Jiayuan Mao, Yu-Hsiang Fu et al.

Extends PAC-Bayes framework to non-compact symmetries, enhancing model generalization.

Armin Beck, Peter Ochs

StreamingThinker enables LLMs to think while reading, reducing 80% token wait and over 60% latency, matching batch performance.

Junlong Tong, Yingqi Fan, Anhao Zhao et al.

In-situ Autoguidance uses dropout self-guidance; on ImageNet 512×512 it reaches FID 2.57 with 50k samples.

Enhao Gu, Haolin Hou