ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Decoder-only model”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.LGcs.AIcs.ITRecentMay 27, 2026

Score Based Error Correcting Code Decoder

Alon Helvits, Eliya Nachmani

The paper introduces SB-ECC, a novel score-based decoder that models error correction as continuous-time denoising, achieving state-of-the-art performance across various code families and noise levels…

View →
cs.SEcs.CRApr 1, 2026

SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models

Kıvanç Kuzey Dikici, Serdar Kara, Semih Çağlar, Eray Tüzün +1 more

SERSEM introduces a selective entropy-weighted scoring framework to significantly improve Membership Inference Attacks (MIAs) against code LLMs by focusing on human-centric coding anomalies rather tha…

View →
cs.LGcs.CLstat.MLTheoreticalRecentJun 29, 2026

When Is a Draft Accepted? A Theory of Acceptance in Speculative Decoding

Aaryam Sharma

This paper develops a theory for speculative decoding in practical language model inference systems, where success is governed by local ranking and threshold events.

View →
cs.CLcs.AIcs.SDRecentMay 29, 2026

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs

Sara Papi, Luisa Bentivogli

The paper proposes DOA, a training-free attention policy that leverages self-attention in decoder-only SpeechLLMs to achieve high-quality, low-latency simultaneous long-form translation without requir…

View →
stat.MLcs.CCcs.DSTheoreticalRecentJul 7, 2026

Boosting with List-Decodable Codes

Addison Prairie, Li-Yang Tan

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

View →
cs.AIEmpiricalRecentNov 4, 2026

Learning to Decode Linear Codes with Generalized Belief Propagation Network

Samira Malek

This paper proposes a Generalized Belief Propagation Network (GBPNet) for error correcting codes that outperforms conventional methods.

View →
cs.ITEmpiricalRecentOct 9, 2026

Neural Polar Codes for Source Coding

Bashar Huleihel, Ziv Aharoni, Haim H. Permuter

This paper presents a data-driven approach to lossless and lossy source compression using polar codes.

View →
cs.CLRecentMay 29, 2026

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models

Humzah Merchant, Bradford Levy

Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…

View →
cs.CLcs.AIRecentMay 31, 2026

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding

Xin Su, Dawid Majchrowski, Fangyuan Yu, Vanshil Atul Shah +4 more

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…

View →
cs.AIRecentMay 30, 2026

Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping

Hanze Li, Jinhao You, Yichen Guo, Kai Tang +2 more

The paper introduces DeLask, a novel decoding framework that dynamically skips or partially aggregates problematic decoder layers to significantly mitigate hallucinations in Large Language Models.

View →
cs.AIRecentMay 28, 2026

Accelerating Constrained Decoding with Token Space Compression

Michael Sullivan, Alexander Koller

The paper introduces CFGzip, an offline token space compression technique that significantly reduces the computational overhead of constrained decoding, making complex grammar enforcement feasible at…

View →
cs.DSTheoreticalRecentJun 9, 2026

Average-Case and Smoothed Near-Optimality for Color-Code Decoding

Daniel Gibney, Jackson Huffstutler

The paper presents a block-based decoder for triangular color-code lattices that achieves strong average-case, smoothed, and sparse-regime guarantees.

View →
math.STstat.MEstat.MLTheoreticalRecentJul 23, 2026

Optimal use of a black-box learner in semiparametric estimation

Yihong Gu

This paper proposes a novel estimator for the target linear coefficient in a partial linear model with black-box nuisance estimation and establishes its unimprovable error rate.

View →
q-bio.NCcs.LGRecentJun 1, 2026

How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations

William Dorrell

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

View →
cs.LGEmpiricalRecentJun 12, 2026

Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens

Ali Asaria, Tony Salomone, Deep Gandhi

Measures decoding order of diffusion models

View →
cs.CLcs.AIRecentJun 1, 2026

SimSD: Simple Speculative Decoding in Diffusion Language Models

Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo +8 more

The paper proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilitie…

View →
cs.LGcs.AIRecentMay 27, 2026

Locality-Aware Redundancy Pruning for LLM Depth Compression

Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo +2 more

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

View →