Cover Image

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Xiangyu, Jiang, Che, Tian, Kai, Qi, Biqing, Sun, Youbang, Ding, Ning, Zhou, Bowen
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
by: Hua, Ermo, et al.
Published: (2024)

On the token distance modeling ability of higher RoPE attention dimension
by: Hong, Xiangyu, et al.
Published: (2024)

CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass
by: Zhang, Bowen, et al.
Published: (2025)

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
by: Ning, Jingjie, et al.
Published: (2026)

Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
by: Hua, Ermo, et al.
Published: (2024)

LLaMA based Punctuation Restoration With Forward Pass Only Decoding
by: Pang, Yutong, et al.
Published: (2024)

On Large Language Models' Hallucination with Regard to Known Facts
by: Jiang, Che, et al.
Published: (2024)

Towards Building Specialized Generalist AI with System 1 and System 2 Fusion
by: Zhang, Kaiyan, et al.
Published: (2024)

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
by: Zhang, Kaiyan, et al.
Published: (2024)

Fine-Tuning Language Models with Just Forward Passes
by: Malladi, Sadhika, et al.
Published: (2023)

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
by: Fu, Dayuan, et al.
Published: (2024)

Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass
by: Popovič, Nicholas, et al.
Published: (2025)

Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
by: Zhang, Kaiyan, et al.
Published: (2024)

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
by: Kolawole, Steven, et al.
Published: (2024)

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks
by: Lyu, Yuanjie, et al.
Published: (2025)

Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
by: Li, Tung-Ling, et al.
Published: (2025)

Towards a Unified View of Large Language Model Post-Training
by: Lv, Xingtai, et al.
Published: (2025)

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
by: Chen, Tong, et al.
Published: (2024)

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
by: Zhang, Jintian, et al.
Published: (2024)

Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning
by: Li, Yilong, et al.
Published: (2026)

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes
by: Christ, Bryan R., et al.
Published: (2024)

TTRL: Test-Time Reinforcement Learning
by: Zuo, Yuxin, et al.
Published: (2025)

Unifying Global and Near-Context Biasing in a Single Trie Pass
by: Thorbecke, Iuliia, et al.
Published: (2024)

PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning
by: Zhu, Xuekai, et al.
Published: (2023)

Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
by: Qi, Biqing, et al.
Published: (2024)

Single-Pass Document Scanning for Question Answering
by: Cao, Weili, et al.
Published: (2025)

SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
by: Yang, Yifan, et al.
Published: (2025)

Large Language Models Pass the Turing Test
by: Jones, Cameron R., et al.
Published: (2025)

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
by: Huang, Yuxiang, et al.
Published: (2025)

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination
by: Zhou, Pengfei, et al.
Published: (2024)

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
by: Long, Xinwei, et al.
Published: (2025)

Aligning Multiple Knowledge Graphs in a Single Pass
by: Yang, Yaming, et al.
Published: (2024)

Cost-of-Pass: An Economic Framework for Evaluating Language Models
by: Erol, Mehmet Hamza, et al.
Published: (2025)

MUSE: Multi-Knowledge Passing on the Edges, Boosting Knowledge Graph Completion
by: Liu, Pengjie
Published: (2024)

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
by: Lv, Xingtai, et al.
Published: (2025)

ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?
by: Ling, Zijian, et al.
Published: (2025)

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
by: Qi, Biqing, et al.
Published: (2024)

DAC: Decomposed Automation Correction for Text-to-SQL
by: Wang, Dingzirui, et al.
Published: (2024)

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
by: Liu, Runze, et al.
Published: (2025)

UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
by: Li, Mengfei, et al.
Published: (2026)