Cover Image

Integral Transformer: Denoising Attention, Not Too Much Not Too Little

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kobyzev, Ivan, Ghaddar, Abbas, Hu, Dingtao, Chen, Boxing
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

BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs
by: Ghaddar, Abbas, et al.
Published: (2026)

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection
by: Huang, Chenyang, et al.
Published: (2024)

ReGLA: Refining Gated Linear Attention
by: Lu, Peng, et al.
Published: (2025)

On the importance of Data Scale in Pretraining Arabic Language Models
by: Ghaddar, Abbas, et al.
Published: (2024)

Too Much Teaching; Too Little Reading
by: Martin, Robert E.
Published: (1969)

Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?
by: Abdulmumin, Idris, et al.
Published: (2024)

Too Helpful, Too Harmless, Too Honest or Just Right?
by: Kashyap, Gautam Siddharth, et al.
Published: (2025)

Expecting Too Much, Getting Too Little: Exploring the Challenges and Design Opportunities of Asynchronous AI Interviewers
by: Sakib, Md Nazmus, et al.
Published: (2026)

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity
by: Metel, Michael R., et al.
Published: (2024)

Live Reference: Too Much, Too Fast?
by: Janes, Joe
Published: (2002)

CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
by: Ghaddar, Abbas, et al.
Published: (2024)

How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness
by: Rathore, Darshita, et al.
Published: (2025)

What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?
by: Karczewski, Rafał, et al.
Published: (2024)

CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search
by: Mo, Fengran, et al.
Published: (2024)

Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs
by: Mahfuz, Tamzeed, et al.
Published: (2024)

To Err Is Human, but Llamas Can Learn It Too
by: Luhtaru, Agnes, et al.
Published: (2024)

Post-edits Are Preferences Too
by: Berger, Nathaniel, et al.
Published: (2024)

Having Too Much
Published: (2023)

Too Little, Too Late: Moderation of Misinformation around the Russo-Ukrainian Conflict
by: Shahi, Gautam Kishore, et al.
Published: (2025)

Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers
by: Barron, Joshua, et al.
Published: (2025)

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
by: Tan, Hexiang, et al.
Published: (2025)

Since the Scientific Literature Is Multilingual, Our Models Should Be Too
by: Ebrahimi, Abteen, et al.
Published: (2024)

Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models
by: Huang, Zemin, et al.
Published: (2025)

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
by: Yi, Zihao, et al.
Published: (2025)

TransAlign: Machine Translation Encoders are Strong Word Aligners, Too
by: Ebing, Benedikt, et al.
Published: (2025)

How Much Is Too Much? Adaptive, Context-Aware Risk Detection in Naturalistic Driving
by: Kalantari, Amir Hossein, et al.
Published: (2025)

Large Language Models can Share Images, Too!
by: Lee, Young-Jun, et al.
Published: (2023)

Too Big to Fool: Resisting Deception in Language Models
by: Samsami, Mohammad Reza, et al.
Published: (2024)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
by: Yuan, Youliang, et al.
Published: (2023)

Too Much of One Thing, Too Little of Another? Comparing Cohesive Networks Between Humans and ChatGPT in Academic Writings and Translations
by: Jia Li
Published: (2026)

List of Australian Subject Headings: Too Little? Too Late?
by: McKinlay, John
Published: (1979)

Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation
by: Ma, Bolei, et al.
Published: (2025)

Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries
by: Biran, Eden, et al.
Published: (2024)

How Do Humans Write Code? Large Models Do It the Same Way Too
by: Li, Long, et al.
Published: (2024)

One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI
by: Clarke, Christopher, et al.
Published: (2024)

Before It's Too Late: A State Space Model for the Early Prediction of Misinformation and Disinformation Engagement
by: Tian, Lin, et al.
Published: (2025)

Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?
by: Choi, Yujin, et al.
Published: (2025)

Hyperparameter Optimization for Large Language Model Instruction-Tuning
by: Tribes, Christophe, et al.
Published: (2023)

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
by: Chen, Chen, et al.
Published: (2024)

Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too
by: Lawrence, Logan, et al.
Published: (2025)