Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking.
Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Despite advances in full-face editing by diffusion-based methods, strong regional controllability, makeup fidelity, and identity preservation remain challenging.
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code.
arXiv:2607. 19431v1 Announce Type: cross Abstract: Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding the speedup.
By Varun Manjunath, Ruokai Yin, Donghyun Lee, Arkapravo Ghosh, Priyadarshini Panda
arXiv:2607. 19935v1 Announce Type: new Abstract: Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs).
By Yu Liu, Zhiwei Yang, Diandian Guo, Kun Peng, Fangfang Yuan, Cong Cao, Chaozhuo Li, Zhiyuan Ma, Yanbing Liu, Guobin Zhao
arXiv:2607. 19686v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging.
By Sijin Chen, Yinuo Ren, Heyang Zhao, Ziheng Cheng, Quanquan Gu, Lexing Ying
arXiv:2607. 19847v1 Announce Type: cross Abstract: Predicting missing cell values in tabular data is a fundamental problem in data cleaning.
By Yurong Liu, Yeye He, Haoyu Dong, Junjie Xing, Shi Han, Dongmei Zhang, Surajit Chaudhuri
arXiv:2607. 19395v1 Announce Type: cross Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets.
By Yihan Wang, Zhong Guan, Haoran Sun, Jiale Huang, Likang Wu, Hongke Zhao
arXiv:2602. 17071v3 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies.
By Rong Fu, Muge Qi, Chunlei Meng, Shuo Yin, Kun Liu, Simon Fong
arXiv:2602. 18047v4 Announce Type: replace-cross Abstract: City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery.
By Rong Fu, Yibo Meng, Jia Yee Tan, Rui Lu, Jiekai Wu, Simon Fong
arXiv:2607. 19360v1 Announce Type: new Abstract: Large language models (LLMs) often answer queries by mapping individual observations to more general rule-like structures.
By Bumjin Park, Jaesik Choi
arXiv:2607. 20225v1 Announce Type: cross Abstract: While combinatorial optimization problems are central to many scientific and engineering applications, their solution remains challenging due to exponentially large search spaces.
By Seongmin Kim, Abhinav Rijal, Yuri Alexeev, Nora Bauer, Martin Roetteler, Mina Yoon, George Siopsis, In-Saeng Suh
arXiv:2607. 20328v1 Announce Type: cross Abstract: This study empirically analyzed generative AI as an emerging discovery pathway to academic library resources.
By Hae Min Kim, Stacy Stanislaw
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
By Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu
arXiv:2512. 16300v3 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (MLLMs) with high-level semantic knowledge.
By Fanrui Zhang, Qiang Zhang, Sizhuo Zhou, Jianwen Sun, Chuanhao Li, Jiaxin Ai, Yukang Feng, Yujie Zhang, Wenjie Li, Zizhen Li, Yifan Chang, Jiawei Liu, Kaipeng Zhang
arXiv:2607. 19366v1 Announce Type: new Abstract: Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K.
By Fumiaki Uehara, Koo Imai, Masato Tsutsumi, Keigo Kansa, Sora Usui, Yuki Kobiyama
arXiv:2607. 19375v1 Announce Type: cross Abstract: Language models perform economically valuable work, yet they are not currently assessed for how well they perform every economically valuable task.
By Alexander Wan, Stephane Hatgis-Kessell, Tom\'as Aguirre, Percy Liang, Rishi Bommasani
arXiv:2607. 19678v1 Announce Type: cross Abstract: AI-generated answers in high-stakes domains are often fluent but difficult to verify, especially when they contain multi-step reasoning rather than a single final answer.
By Guneet Singh Kohli, Yuxiang Zhou, Michael Sejr Schlichtkrull, Gregory E Dean, Maria Liakata
arXiv:2607. 19973v1 Announce Type: new Abstract: AI researchers describe state-of-the-art models as one thing repeated at scale: the Transformer, wired identically for text, pixels, or speech.
By Jaeho Seol
arXiv:2607. 20323v1 Announce Type: new Abstract: Nanopore devices have emerged as powerful tools for single-molecule sensing, with potential for rapid, portable diagnostics.
By Sandro Kuppel, Julian Ho{\ss}bach, Samuel Tovey, Christian Holm