Résultats de la recherche - (coding OR Decoding) (algorithm OR (algorithmsssic OR algorithmsssic))

Language Models that Think, Chat Better par Bhaskar, Adithya, Ye, Xi, Chen, Danqi

Table des matières: “… rule-based rewards in verifiable domains such as mathematics and code. However, RLVR leads to limited…”
Accéder au texte intégral

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

Table des matières: “… exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its…”
Accéder au texte intégral

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

Table des matières: “…, it enhances the path expansion through a Monte Carlo algorithm with a temporally adaptive policy that begins…”
Accéder au texte intégral

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

Table des matières: “…-SPO), a novel training algorithm that alternates between Self-Play and reinforcement learning…”
Accéder au texte intégral

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

Table des matières: “… after which they can no longer be saved.For Time-PD,we present color-coding algorithms that prove…”
Accéder au texte intégral

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

Table des matières: “… propose a label-guided distillation algorithm to distill open-vocabulary knowledge from label-consistent 2…”
Accéder au texte intégral

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

Table des matières: “… the distribution of hyper-edges on each forward pass. Additionally, the model adapts the standard MAE algorithm…”
Accéder au texte intégral

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

Table des matières: “… \underline{AdamW} algorithm, called \texttt{FedAdamW}, for training and fine-tuning various large models…”
Accéder au texte intégral

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

Table des matières: “… automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case…”
Accéder au texte intégral

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

Table des matières: “… the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties…”
Accéder au texte intégral

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

Table des matières: “… object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut…”
Accéder au texte intégral

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

Table des matières: “… for GPUs. Spira proposes (i) a high-performance one-shot search algorithm that builds the kernel map…”
Accéder au texte intégral

MICCAI STS 2024 Challenge: Semi-Supervised Instance-Level Tooth Segmentation in Panoramic X-ray and CBCT Images par 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 des matières: “…) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid…”
Accéder au texte intégral

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

Table des matières: “… optimization (GRPO), which is a commonly used RLVR algorithm. Our code is available at https://github.com…”
Accéder au texte intégral

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

Table des matières: “… of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement…”
Accéder au texte intégral

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

Table des matières: “… an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching…”
Accéder au texte intégral

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

Table des matières: “… algorithm that adapts fusion schemes to different GPU architectures. To further improve performance, HERO…”
Accéder au texte intégral

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

Table des matières: “… algorithms that leverage both first-order preferences and second-order predictions in ranking tasks. Each…”
Accéder au texte intégral

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

Table des matières: “… evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight…”
Accéder au texte intégral

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

Table des matières: “… access to the underlying code or full model operators, i.e., non-intrusively. Traditional OpInf operates…”
Accéder au texte intégral