Search Results - decoding (algorithmics OR (algorithm OR (Algorithmsssics OR (algorithm OR algorithm))))

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

Table of Contents: “… Feedback (RLHF) algorithms for aligning large language models (LLMs) with human preferences. However, DAAs…”
Get full text

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

Table of Contents: “… ones, and beam search is commonly used to balance exploration and fluency during decoding. While deep…”
Get full text

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

Table of Contents: “…, including: (1) encoder-only or decoder-only LLMs, (2) prompt-based parameter-efficient fine-tuning (PEFT…”
Get full text

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

Table of Contents: “… an instruction-agnostic token compression algorithm based on a plug-and-play visual decoder to improve decoding…”
Get full text

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

Table of Contents: “…, we introduce STARS, Synchronous Token Alignment for Robust Supervision, a decoding-time algorithm…”
Get full text

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

Table of Contents: “… algorithms explore exponentially large Hilbert spaces. We recast qubit-efficient optimization as a geometric…”
Get full text

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

Table of Contents: “… generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm…”
Get full text

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

Table of Contents: “… with sampling strategies beyond greedy decoding. Our experiments validate that simple thresholding of the metric…”
Get full text

Hold Onto That Thought: Assessing KV Cache Compression On Reasoning by 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

Table of Contents: “… attention computations, grows linearly with context length. A suite of compression algorithms has been…”
Get full text

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

Table of Contents: “… inference. However, current confidence-driven decoding strategies are constrained by limited parallelism…”
Get full text

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding by Li, Huayu, He, ZhengXiao, Tian, Siyuan, Wen, Jinghao, Li, Ao

Table of Contents: “…Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often…”
Get full text

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models by Bai, Jinbin, Li, Yixuan, Zhu, Yuchen, Xin, Yi, Shi, Qingyu, Feng, Aosong, Liu, Xiaohong, Tao, Molei, Xue, Jianru, Li, Xiangtai, Yang, Ming-Hsuan

Table of Contents: “… scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion…”
Get full text

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL by Wu, Ian, Qu, Yuxiao, Setlur, Amrith, Kumar, Aviral

Table of Contents: “… RC, an iterative decoding algorithm that replaces standard autoregressive decoding during both…”
Get full text

Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement by Subbalakshmi, Koduvayur, Ujjal, Sabbir Hossain, Mangichetty, Venkata Krishna Teja, Soofi, Nastaran Jamalipour

Table of Contents: “… Aware) decoder, a novel, training-free decoding algorithm that mitigates hallucinations at inference…”
Get full text

ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos by Seminara, Luigi, Moltisanti, Davide, Furnari, Antonino

Table of Contents: “… with the Viterbi decoding algorithm, replacing non-differentiable operations with smooth relaxations that enable…”
Get full text

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space by Wang, Peihao, Cai, Ruisi, Wang, Zhen, Mei, Hongyuan, Liu, Qiang, Li, Pan, Wang, Zhangyang

Table of Contents: “… and suboptimal discrete search algorithms or trial-and-error prompting to improve the online policy…”
Get full text

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling by Nguyen, Tu, Zimmer, Matthieu, Tutunov, Rasul, Ji, Xiaotong, Ammar, Haitham Bou

Table of Contents: “… at inference time. Power sampling provides a principled way to bias decoding toward such modes by targeting…”
Get full text

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs by Lu, Haiquan, Chen, Zigeng, Fang, Gongfan, Ma, Xinyin, Wang, Xinchao

Table of Contents: “… preserving BF16 precision for decoding. By decoupling prefilling acceleration from decoding quality, Mix…”
Get full text

Best-First Ordered Statistics Decoding of Quantum LDPC Codes by Banfi, Michele, Ferrari, Marco, Favano, Antonino, Tarable, Alberto, Barletta, Luca

Table of Contents: “… standard for decoding quantum low-density parity-check (QLDPC) codes. Recent advancements in this field…”
Get full text

NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies by Chen, Zhiyang, Xu, Daliang, Zhang, Yinyuan, Wang, Chenghua, Xu, Mengwei, Ma, Yun

Table of Contents: “… computational bottleneck on the final linear projection layer during speculative decoding. Existing vocabulary…”
Get full text