Cover Image

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sengupta, Ayan, Chaudhary, Siddhant, Chakraborty, Tanmoy
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

Compression Laws for Large Language Models
by: Sengupta, Ayan, et al.
Published: (2025)

Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
by: Sengupta, Ayan, et al.
Published: (2025)

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics
by: Ananthanarayanan, Samhruth, et al.
Published: (2026)

The Art of Scaling Test-Time Compute for Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2025)

First Finish Search: Efficient Test-Time Scaling in Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2025)

Position: Enough of Scaling LLMs! Lets Focus on Downscaling
by: Goel, Yash, et al.
Published: (2025)

Persona-aware Generative Model for Code-mixed Language
by: Sengupta, Ayan, et al.
Published: (2023)

How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines
by: Sengupta, Ayan, et al.
Published: (2025)

On the Generalization vs Fidelity Paradox in Knowledge Distillation
by: Ramesh, Suhas Kamasetty, et al.
Published: (2025)

Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2024)

From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
by: Sengupta, Ayan, et al.
Published: (2026)

You Only Cache Once: Decoder-Decoder Architectures for Language Models
by: Sun, Yutao, et al.
Published: (2024)

You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL
by: Kobayashi, Hideo, et al.
Published: (2024)

MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
by: Agarwal, Siddhant, et al.
Published: (2024)

You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
by: Qin, Zhen, et al.
Published: (2024)

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
by: Xiang, Yang, et al.
Published: (2025)

You Only Fine-tune Once: Many-Shot In-Context Fine-Tuning for Large Language Models
by: He, Wenchong, et al.
Published: (2025)

CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs
by: Hengle, Amey, et al.
Published: (2025)

Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models
by: Sharma, Shivam, et al.
Published: (2025)

Latent Performance Profiling of Large Language Models
by: Chakraborty, Tanmoy, et al.
Published: (2026)

You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
by: Hsing, Nicole, et al.
Published: (2026)

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation
by: Sengupta, Ayan, et al.
Published: (2024)

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
by: Luo, Wen, et al.
Published: (2026)

Multilingual Test-Time Scaling via Initial Thought Transfer
by: Bajpai, Prasoon, et al.
Published: (2025)

Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues
by: Kumar, Shivani, et al.
Published: (2024)

Information Anxiety in Large Language Models
by: Bajpai, Prasoon, et al.
Published: (2024)

Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning
by: Kumar, Aswini, et al.
Published: (2025)

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks
by: Chatterjee, Anwoy, et al.
Published: (2024)

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models
by: Nandi, Palash, et al.
Published: (2025)

Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge
by: Tanwar, Eshaan, et al.
Published: (2025)

You Only Train Once
by: Sakaridis, Christos
Published: (2025)

Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling
by: Hajra, Suvadeep, et al.
Published: (2026)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
by: Jiang, Titong, et al.
Published: (2025)

Mechanistic Behavior Editing of Language Models
by: Singh, Joykirat, et al.
Published: (2024)

You Only Speak Once to See
by: Yang, Wenhao, et al.
Published: (2024)

coTherapist: A Behavior-Aligned Small Language Model to Support Mental Healthcare Experts
by: Adhikary, Prottay Kumar, et al.
Published: (2026)

Free(): Learning to Forget in Malloc-Only Reasoning Models
by: Zheng, Yilun, et al.
Published: (2026)

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
by: Chatterjee, Anwoy, et al.
Published: (2025)

Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities
by: Mandal, Aishik, et al.
Published: (2025)

$\texttt{LM}^\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning
by: Juneja, Gurusha, et al.
Published: (2024)