Cover Image

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yoon, Kanghoon, Kim, Minsub, Lee, Sungjae, Lee, Joonhyung, Woo, Sunghyeon, In, Yeonjun, Kwon, Se Jung, Park, Chanyoung, Lee, Dongsoo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
by: Lee, Jeongtae, et al.
Published: (2026)

Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
by: Bae, Jeongin, et al.
Published: (2026)

Debiased Graph Poisoning Attack via Contrastive Surrogate Objective
by: Yoon, Kanghoon, et al.
Published: (2024)

Self-Guided Robust Graph Structure Refinement
by: In, Yeonjun, et al.
Published: (2024)

Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness
by: Kim, Junghoon, et al.
Published: (2024)

ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
by: Woo, Sunghyeon, et al.
Published: (2026)

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
by: Park, Gunho, et al.
Published: (2022)

Adaptive Self-training Framework for Fine-grained Scene Graph Generation
by: Kim, Kibum, et al.
Published: (2024)

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
by: Kim, Kibum, et al.
Published: (2025)

To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability
by: Lee, Joonhyung, et al.
Published: (2024)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
by: In, Yeonjun, et al.
Published: (2026)

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
by: Kim, Sein, et al.
Published: (2026)

DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
by: Woo, Sunghyeon, et al.
Published: (2024)

An Inquiry into Datacenter TCO for LLM Inference with FP8
by: Kim, Jiwoo, et al.
Published: (2025)

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning
by: Yoon, Kanghoon, et al.
Published: (2024)

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
by: Kim, Kibum, et al.
Published: (2023)

SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

Training Robust Graph Neural Networks by Modeling Noise Dependencies
by: In, Yeonjun, et al.
Published: (2025)

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
by: Lee, Jung Hyun, et al.
Published: (2023)

Faster Inference of LLMs using FP8 on the Intel Gaudi
by: Lee, Joonhyung, et al.
Published: (2025)

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
by: In, Yeonjun, et al.
Published: (2025)

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
by: Kim, Sungkyun, et al.
Published: (2025)

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
by: Kim, Wonjoong, et al.
Published: (2026)

AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
by: Park, Gunho, et al.
Published: (2025)

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
by: Bachmann, Gregor, et al.
Published: (2025)

Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation
by: Jeon, Jaehyeong, et al.
Published: (2024)

Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
by: Kim, Wonjoong, et al.
Published: (2025)

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
by: Heo, Jung Hwan, et al.
Published: (2023)

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
by: In, Yeonjun, et al.
Published: (2025)

Reasoning Structure Matters for Safety Alignment of Reasoning Models
by: In, Yeonjun, et al.
Published: (2026)

Token-Efficient Item Representation via Images for LLM Recommender Systems
by: Kim, Kibum, et al.
Published: (2025)

Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
by: Seo, Sangwoo, et al.
Published: (2024)

Self-Speculative Biased Decoding for Faster Re-Translation
by: Zeng, Linxiao, et al.
Published: (2025)

Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
by: Park, Seungcheol, et al.
Published: (2025)

No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
by: Yang, June Yong, et al.
Published: (2024)

Multi-Drafter Speculative Decoding with Alignment Feedback
by: Kim, Taehyeon, et al.
Published: (2026)

ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
by: Woo, Sungmin, et al.
Published: (2024)

Faster Cascades via Speculative Decoding
by: Narasimhan, Harikrishna, et al.
Published: (2024)

Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
by: Lee, Dongryeol, et al.
Published: (2026)