Resultados de búsqueda - decoding (algorithm OR (Algorithmsssic OR Algorithmsssic))

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models por Zhang, Ce, Wan, Zifu, Kan, Zhehan, Ma, Martin Q., Stepputtis, Simon, Ramanan, Deva, Salakhutdinov, Russ, Morency, Louis-Philippe, Sycara, Katia, Xie, Yaqi

Tabla de Contenidos: “… Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from…”
Enlace del recurso

Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment por Favero, Lucile, Pérez-Ortiz, Juan Antonio, Käser, Tanja, Oliver, Nuria

Tabla de Contenidos: “…Argument mining algorithms analyze the argumentative structure of essays, making them a valuable…”
Enlace del recurso

STAR-RIS-aided NOMA for Secured xURLLC por Lulu, Song, Di, Zhang, Shaobo, Jia, Pengcheng, Zhu, Yonghui, Li

Tabla de Contenidos: “…), which provides additional degree of freedom to enable a secure and fair decoding order and achieve a…”
Enlace del recurso

SigChord: Sniffing Wide Non-sparse Multiband Signals for Terrestrial and Non-terrestrial Wireless Networks por Peng, Jinbo, Duan, Junwen, Lin, Zheng, Yuan, Haoxuan, Gao, Yue, Chen, Zhe

Tabla de Contenidos: “… on low-cost and sub-Nyquist sampling radios. We first design a deep and rule-based interleaving algorithm…”
Enlace del recurso

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting por Xu, Jiaming, Pan, Jiayi, Zhou, Yongkang, Chen, Siming, Li, Jinhao, Lian, Yaoxiu, Wu, Junyi, Dai, Guohao

Tabla de Contenidos: “… SpecEE, a fast LLM inference engine with speculative early exiting. (1) At the algorithm level, we…”
Enlace del recurso

LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment por Long, Jiahuan, Zhou, Xin

Tabla de Contenidos: “…, existing depth estimation algorithms often struggle to effectively balance performance and computational…”
Enlace del recurso

Antenna Activation and Resource Allocation in Multi-Waveguide Pinching-Antenna Systems por Wang, Kaidi, Ding, Zhiguo, Karagiannidis, George K.

Tabla de Contenidos: “…-theoretic algorithm is developed, in which the optimal decoding order is derived and incorporated. For power…”
Enlace del recurso

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models por Gu, Haoran, Wang, Handing, Mei, Yi, Zhang, Mengjie, Jin, Yaochu

Tabla de Contenidos: “… simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens…”
Enlace del recurso

Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency por Li, Ruixiao, Chen, Fahao, Li, Peng

Tabla de Contenidos: “…Speculative decoding accelerates Large Language Model (LLM) inference by employing a small…”
Enlace del recurso

An Exploratory Framework for Future SETI Applications: Detecting Generative Reactivity via Language Models por Yu, Po-Chieh

Tabla de Contenidos: “… responses in language models. Instead of assuming that extraterrestrial signals must be decoded, we evaluate…”
Enlace del recurso

Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms por Xiao, Zeguan, Chen, Yun, Chen, Guanhua, Tang, Ke

Tabla de Contenidos: “… Feedback (RLHF) algorithms for aligning large language models (LLMs) with human preferences. However, DAAs…”
Enlace del recurso

ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search por Collura, Vincenzo, Tit, Karim, Bussi, Laura, Giunchiglia, Eleonora, Cordy, Maxime

Tabla de Contenidos: “… ones, and beam search is commonly used to balance exploration and fluency during decoding. While deep…”
Enlace del recurso

A Study of Large Language Models for Patient Information Extraction: Model Architecture, Fine-Tuning Strategy, and Multi-task Instruction Tuning por Peng, Cheng, Dong, Xinyu, Lyu, Mengxian, Paredes, Daniel, Zhang, Yaoyun, Wu, Yonghui

Tabla de Contenidos: “…, including: (1) encoder-only or decoder-only LLMs, (2) prompt-based parameter-efficient fine-tuning (PEFT…”
Enlace del recurso

Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models por Li, Yueyan, Zhao, Chenggong, Zang, Zeyuan, Yuan, Caixia, Wang, Xiaojie

Tabla de Contenidos: “… an instruction-agnostic token compression algorithm based on a plug-and-play visual decoder to improve decoding…”
Enlace del recurso

STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models por Quamar, Mohammad Atif, Areeb, Mohammad, Kuznetsov, Mikhail, Ozmen, Muslum Ozgur, Celik, Z. Berkay

Tabla de Contenidos: “…, we introduce STARS, Synchronous Token Alignment for Robust Supervision, a decoding-time algorithm…”
Enlace del recurso

An Information-Minimal Geometry for Qubit-Efficient Optimization por Ma, Gordon, Angelakis, Dimitris G.

Tabla de Contenidos: “… algorithms explore exponentially large Hilbert spaces. We recast qubit-efficient optimization as a geometric…”
Enlace del recurso

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning por Zhang, Chubin, Wan, Zhenglin, Chen, Feng, Yang, Fuchao, Feng, Lang, Zhou, Yaxin, Yu, Xingrui, You, Yang, Tsang, Ivor, An, Bo

Tabla de Contenidos: “… generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm…”
Enlace del recurso

Short-Context Dominance: How Much Local Context Natural Language Actually Needs? por Vakilian, Vala, Wang, Zimeng, Rawat, Ankit Singh, Thrampoulidis, Christos

Tabla de Contenidos: “… with sampling strategies beyond greedy decoding. Our experiments validate that simple thresholding of the metric…”
Enlace del recurso

Hold Onto That Thought: Assessing KV Cache Compression On Reasoning por Liu, Minghui, Palnitkar, Aadi, Rabbani, Tahseen, Jae, Hyunwoo, Sang, Kyle Rui, Yao, Dixi, Shabihi, Shayan, Zhao, Fuheng, Li, Tian, Zhang, Ce, Huang, Furong, Zhang, Kunpeng

Tabla de Contenidos: “… attention computations, grows linearly with context length. A suite of compression algorithms has been…”
Enlace del recurso

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding por Xu, Chenkai, Jin, Yijie, Li, Jiajun, Tu, Yi, Long, Guoping, Tu, Dandan, Song, Mingcong, Si, Hongjie, Hou, Tianqi, Yan, Junchi, Deng, Zhijie

Tabla de Contenidos: “… inference. However, current confidence-driven decoding strategies are constrained by limited parallelism…”
Enlace del recurso