Search Results - coding (((algorithmics OR algorithmssics) OR algorithmicsics) OR (algorithm OR algorithm))

Active Attacks: Red-teaming LLMs via Adaptive Environments by Yun, Taeyoung, St-Charles, Pierre-Luc, Park, Jinkyoo, Bengio, Yoshua, Kim, Minsu

Table of Contents: “… exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its…”
Get full text

From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision by Ma, Jie, Qi, Shihao, Xing, Rui, Yin, Ziang, Wei, Bifan, Liu, Jun, Liu, Tongliang

Table of Contents: “…, it enhances the path expansion through a Monte Carlo algorithm with a temporally adaptive policy that begins…”
Get full text

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play by Wang, Qinsi, Liu, Bo, Zhou, Tianyi, Shi, Jing, Lin, Yueqian, Chen, Yiran, Li, Hai Helen, Wan, Kun, Zhao, Wentian

Table of Contents: “…-SPO), a novel training algorithm that alternates between Self-Play and reinforcement learning…”
Get full text

Who Should Have a Place on the Ark? Parameterized Algorithms for the Maximization of Phylogenetic Diversity by Schestag, Jannik

Table of Contents: “… after which they can no longer be saved.For Time-PD,we present color-coding algorithms that prove…”
Get full text

FOLK: Fast Open-Vocabulary 3D Instance Segmentation via Label-guided Knowledge Distillation by Wu, Hongrui, Gao, Zhicheng, Cao, Jin, Yao, Kelu, Shen, Wen, Wei, Zhihua

Table of Contents: “… propose a label-guided distillation algorithm to distill open-vocabulary knowledge from label-consistent 2…”
Get full text

Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning by Mihai-Cristian, Pîrvu, Leordeanu, Marius

Table of Contents: “… the distribution of hyper-edges on each forward pass. Additionally, the model adapts the standard MAE algorithm…”
Get full text

FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models by Liu, Junkang, Shang, Fanhua, Liu, Hongying, Tian, Yuxuan, Liu, Yuanyuan, Liu, Jin, Zhu, Kewen, Lin, Zhouchen

Table of Contents: “… \underline{AdamW} algorithm, called \texttt{FedAdamW}, for training and fine-tuning various large models…”
Get full text

CORGI: Efficient Pattern Matching With Quadratic Guarantees by Weitekamp, Daniel

Table of Contents: “… automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case…”
Get full text

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping by Huang, Yushi, Wang, Zining, Yuan, Zhihang, Ding, Yifu, Gong, Ruihao, Guo, Jinyang, Liu, Xianglong, Zhang, Jun

Table of Contents: “… the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties…”
Get full text

Solving Spatial Supersensing Without Spatial Supersensing by Udandarao, Vishaal, Karthik, Shyamgopal, Nath, Surabhi S., Hochlehnert, Andreas, Bethge, Matthias, Prabhu, Ameya

Table of Contents: “… object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut…”
Get full text

Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks by Adamopoulos, Dionysios, Poulopoulou, Anastasia, Goumas, Georgios, Giannoula, Christina

Table of Contents: “… for GPUs. Spira proposes (i) a high-performance one-shot search algorithm that builds the kernel map…”
Get full text

MICCAI STS 2024 Challenge: Semi-Supervised Instance-Level Tooth Segmentation in Panoramic X-ray and CBCT Images by Wang, Yaqi, Li, Zhi, Wu, Chengyu, Liu, Jun, Zhang, Yifan, Ni, Jiaxue, Luo, Qian, Chen, Jialuo, Zhang, Hongyuan, Liu, Jin, Han, Can, Fu, Kaiwen, Ji, Changkai, Cai, Xinxu, Hao, Jing, Zheng, Zhihao, Xu, Shi, Chen, Junqiang, Zhang, Qianni, Qian, Dahong, Wang, Shuai, Zhou, Huiyu

Table of Contents: “…) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid…”
Get full text

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning by Mitra, Purbesh, Ulukus, Sennur

Table of Contents: “… optimization (GRPO), which is a commonly used RLVR algorithm. Our code is available at https://github.com…”
Get full text

How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline by Zhang, Chunhui, Liu, Li, Zhang, Zhipeng, Wang, Yong, Wen, Hao, Zhou, Xi, Ge, Shiming, Wang, Yanfeng

Table of Contents: “… of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement…”
Get full text

TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning by Yang, Shenzhi, Zhu, Guangcheng, Zheng, Xing, MA, Yingfan, Chen, Zhongqi, Song, Bowen, Wang, Weiqiang, Zhao, Junbo, Chen, Gang, Wang, Haobo

Table of Contents: “… an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching…”
Get full text

HERO-Sign: Hierarchical Tuning and Efficient Compiler-Time GPU Optimizations for SPHINCS+ Signature Generation by Zhou, Yaoyun, Wang, Qian

Table of Contents: “… algorithm that adapts fusion schemes to different GPU architectures. To further improve performance, HERO…”
Get full text

SP-Rank: A Dataset for Ranked Preferences with Secondary Information by Hosseini, Hadi, Mandal, Debmalya, Puhan, Amrit

Table of Contents: “… algorithms that leverage both first-order preferences and second-order predictions in ranking tasks. Each…”
Get full text

TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents by Wang, Dawei, Zhou, Chengming, Zhao, Di, Liu, Xinyuan, Ma, Marci Chi, Ushaw, Gary, Davison, Richard

Table of Contents: “… evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight…”
Get full text

Streaming Operator Inference for Model Reduction of Large-Scale Dynamical Systems by Koike, Tomoki, Mohan, Prakash, de Frahan, Marc T. Henry, Bessac, Julie, Qian, Elizabeth

Table of Contents: “… access to the underlying code or full model operators, i.e., non-intrusively. Traditional OpInf operates…”
Get full text

FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design by Zhang, Jiahao, He, Zifan, Fraser, Nicholas, Blott, Michaela, Sun, Yizhou, Cong, Jason

Table of Contents: “… lines of code. The system includes: (1) a stage-customized accelerator with hardware-efficient…”
Get full text