20 results for “Decoder-only model”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
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…
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…
This paper develops a theory for speculative decoding in practical language model inference systems, where success is governed by local ranking and threshold events.
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…
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…
This paper proposes a Generalized Belief Propagation Network (GBPNet) for error correcting codes that outperforms conventional methods.
This paper presents a data-driven approach to lossless and lossy source compression using polar codes.
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…
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…
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.
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…
The paper presents a block-based decoder for triangular color-code lattices that achieves strong average-case, smoothed, and sparse-regime guarantees.
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.
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…
Measures decoding order of diffusion 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…
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…