Cover Image

Think Clearly: Improving Reasoning via Redundant Token Pruning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Choi, Daewon, Lee, Jimin, Tack, Jihoon, Song, Woomin, Dingliwal, Saket, Jayanthi, Sai Muralidhar, Ganesh, Bhavana, Shin, Jinwoo, Galstyan, Aram, Bodapati, Sravan Babu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Accelerated Test-Time Scaling with Model-Free Speculative Sampling
by: Song, Woomin, et al.
Published: (2025)

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
by: Choi, Daewon, et al.
Published: (2026)

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
by: Song, Woomin, et al.
Published: (2026)

Mamba Drafters for Speculative Decoding
by: Choi, Daewon, et al.
Published: (2025)

SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
by: Ko, Jongwoo, et al.
Published: (2024)

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers
by: Song, Woomin, et al.
Published: (2025)

Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning
by: Jeoung, Sullam, et al.
Published: (2024)

Sparsified State-Space Models are Efficient Highway Networks
by: Song, Woomin, et al.
Published: (2025)

Wanda++: Pruning Large Language Models via Regional Gradients
by: Yang, Yifan, et al.
Published: (2025)

ReMoDetect: Reward Models Recognize Aligned LLM's Generations
by: Lee, Hyunseok, et al.
Published: (2024)

Beyond Correctness: Learning Robust Reasoning via Transfer
by: Lee, Hyunseok, et al.
Published: (2026)

Tabular Transfer Learning via Prompting LLMs
by: Nam, Jaehyun, et al.
Published: (2024)

SpeechVerse: A Large-scale Generalizable Audio Language Model
by: Das, Nilaksh, et al.
Published: (2024)

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
by: Lee, Hyunseok, et al.
Published: (2025)

Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions
by: Kim, Junbeom, et al.
Published: (2025)

Adversarial Robustification via Text-to-Image Diffusion Models
by: Choi, Daewon, et al.
Published: (2024)

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
by: Nam, Jaehyun, et al.
Published: (2024)

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
by: Du, Yufeng, et al.
Published: (2025)

Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting
by: Ahn, Jinwoo, et al.
Published: (2024)

Online Adaptation of Language Models with a Memory of Amortized Contexts
by: Tack, Jihoon, et al.
Published: (2024)

Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
by: Xu, Lei, et al.
Published: (2024)

Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark
by: Huybrechts, Goeric, et al.
Published: (2025)

SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
by: Peri, Raghuveer, et al.
Published: (2024)

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
by: Lee, Dongjun, et al.
Published: (2025)

Sequential Editing for Lifelong Training of Speech Recognition Models
by: Kulshreshtha, Devang, et al.
Published: (2024)

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
by: Lee, Yuna, et al.
Published: (2026)

ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models
by: Elangovan, Aparna, et al.
Published: (2024)

Making Sense Of Distributed Representations With Activation Spectroscopy
by: Reing, Kyle, et al.
Published: (2025)

Learning Morphisms with Gauss-Newton Approximation for Growing Networks
by: Lawton, Neal, et al.
Published: (2024)

Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
by: Feng, Qizhang, et al.
Published: (2024)

HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
by: Koo, Myungkyu, et al.
Published: (2025)

LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
by: Liu, Zeyu, et al.
Published: (2025)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
by: Bagrov, Natan, et al.
Published: (2025)

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
by: Ovalle, Anaelia, et al.
Published: (2023)

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
by: Song, Woomin, et al.
Published: (2024)

ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search
by: Lee, Hyunseok, et al.
Published: (2025)

DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer ASR
by: Huybrechts, Goeric, et al.
Published: (2023)

Scott–Russel Linkage‐Based Triboelectric Self‐Powered Sensor for Contact Material‐Independent Force Sensing and Tactile Recognition
by: Dongwon Seo, et al.
Published: (2024)

Deep Minimax Classifiers for Imbalanced Datasets with a Small Number of Minority Samples
by: Choi, Hansung, et al.
Published: (2025)

Feature Importance-Aware Deep Joint Source-Channel Coding for Computationally Efficient and Adjustable Image Transmission
by: Choi, Hansung, et al.
Published: (2025)