Cover Image

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Massoli, Fabio Valerio, Kuzmin, Andrey, Behboodi, Arash
Format:	Preprint
Published:	2026
Subjects:	Machine Learning I.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Variational Learning ISTA
by: Massoli, Fabio Valerio, et al.
Published: (2024)

An Information Theoretic Perspective on Conformal Prediction
by: Correia, Alvaro H. C., et al.
Published: (2024)

Simulating, Fast and Slow: Learning Policies for Black-Box Optimization
by: Massoli, Fabio Valerio, et al.
Published: (2024)

Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems
by: Silvestri, Gianluigi, et al.
Published: (2024)

Vision-Assisted Digital Twin Creation for mmWave Beam Management
by: Arnold, Maximilian, et al.
Published: (2024)

Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction
by: Behboodi, Arash, et al.
Published: (2025)

The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference
by: Sairam, S, et al.
Published: (2025)

Label Smoothing is a Pragmatic Information Bottleneck
by: Kudo, Sota
Published: (2025)

Pruning vs Quantization: Which is Better?
by: Kuzmin, Andrey, et al.
Published: (2023)

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
by: He, Langzhou, et al.
Published: (2026)

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
by: Salfati, Samuel
Published: (2026)

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
by: Vendrell, Victor Conchello, et al.
Published: (2026)

The Shortcomings of Force-from-Motion in Robot Learning
by: Aljalbout, Elie, et al.
Published: (2024)

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
by: Nakamura, Mason, et al.
Published: (2025)

Ensemble based Closed-Loop Optimal Control using Physics-Informed Neural Networks
by: Barry-Straume, Jostein, et al.
Published: (2025)

On the Limits of Learned Importance Scoring for KV Cache Compression
by: Steele, Brady
Published: (2026)

Distributional Reinforcement Learning for Condition-Based Maintenance of Multi-Pump Equipment
by: Yasuno, Takato
Published: (2026)

On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL
by: Belcamino, Valerio, et al.
Published: (2026)

Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation
by: Dwivedi, Abhay Kumar, et al.
Published: (2025)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
by: Panuganti, Rajkiran
Published: (2026)

Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
by: Jaber, Jaber, et al.
Published: (2026)

LLM Vocabulary Compression for Low-Compute Environments
by: Vennam, Sreeram, et al.
Published: (2024)

Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities
by: Krylov, Andrey, et al.
Published: (2026)

Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game
by: Li, Lixing
Published: (2026)

The Curious Case of In-Training Compression of State Space Models
by: Chahine, Makram, et al.
Published: (2025)

Downsized and Compromised?: Assessing the Faithfulness of Model Compression
by: Kamal, Moumita, et al.
Published: (2025)

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring
by: Heyman, Alex, et al.
Published: (2025)

Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization
by: Wang, Yuanchao, et al.
Published: (2026)

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation
by: Chang, Wei-Jer, et al.
Published: (2025)

Approach to Finding a Robust Deep Learning Model
by: Boldyrev, Alexey, et al.
Published: (2025)

Memory Bank Compression for Continual Adaptation of Large Language Models
by: Katraouras, Thomas, et al.
Published: (2026)

Carefully Structured Compression: Efficiently Managing StarCraft II Data
by: Ferenczi, Bryce, et al.
Published: (2024)

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
by: Zimerman, Itamar, et al.
Published: (2024)

Large Language Models Are Not Strong Abstract Reasoners
by: Gendron, Gaël, et al.
Published: (2023)

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
by: Lan, Guangchen, et al.
Published: (2025)

Avoiding Death through Fear Intrinsic Conditioning
by: Sanchez, Rodney, et al.
Published: (2025)

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
by: Rath, Plawan Kumar, et al.
Published: (2026)

BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks
by: Gandhi, Shubham, et al.
Published: (2024)

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control
by: Hiremath, Prakul Sunil
Published: (2026)

D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning
by: Wang, Caroline, et al.
Published: (2022)