Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Massoli, Fabio Valerio, Kuzmin, Andrey, Behboodi, Arash
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning I.2
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Variational Learning ISTA
par: Massoli, Fabio Valerio, et autres
Publié: (2024)

An Information Theoretic Perspective on Conformal Prediction
par: Correia, Alvaro H. C., et autres
Publié: (2024)

Simulating, Fast and Slow: Learning Policies for Black-Box Optimization
par: Massoli, Fabio Valerio, et autres
Publié: (2024)

Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems
par: Silvestri, Gianluigi, et autres
Publié: (2024)

Vision-Assisted Digital Twin Creation for mmWave Beam Management
par: Arnold, Maximilian, et autres
Publié: (2024)

Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction
par: Behboodi, Arash, et autres
Publié: (2025)

The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference
par: Sairam, S, et autres
Publié: (2025)

Label Smoothing is a Pragmatic Information Bottleneck
par: Kudo, Sota
Publié: (2025)

Pruning vs Quantization: Which is Better?
par: Kuzmin, Andrey, et autres
Publié: (2023)

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
par: He, Langzhou, et autres
Publié: (2026)

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

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
par: Vendrell, Victor Conchello, et autres
Publié: (2026)

The Shortcomings of Force-from-Motion in Robot Learning
par: Aljalbout, Elie, et autres
Publié: (2024)

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
par: Nakamura, Mason, et autres
Publié: (2025)

Ensemble based Closed-Loop Optimal Control using Physics-Informed Neural Networks
par: Barry-Straume, Jostein, et autres
Publié: (2025)

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

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

On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL
par: Belcamino, Valerio, et autres
Publié: (2026)

Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation
par: Dwivedi, Abhay Kumar, et autres
Publié: (2025)

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

Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
par: Jaber, Jaber, et autres
Publié: (2026)

LLM Vocabulary Compression for Low-Compute Environments
par: Vennam, Sreeram, et autres
Publié: (2024)

Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities
par: Krylov, Andrey, et autres
Publié: (2026)

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

The Curious Case of In-Training Compression of State Space Models
par: Chahine, Makram, et autres
Publié: (2025)

Downsized and Compromised?: Assessing the Faithfulness of Model Compression
par: Kamal, Moumita, et autres
Publié: (2025)

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring
par: Heyman, Alex, et autres
Publié: (2025)

Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization
par: Wang, Yuanchao, et autres
Publié: (2026)

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation
par: Chang, Wei-Jer, et autres
Publié: (2025)

Approach to Finding a Robust Deep Learning Model
par: Boldyrev, Alexey, et autres
Publié: (2025)

Memory Bank Compression for Continual Adaptation of Large Language Models
par: Katraouras, Thomas, et autres
Publié: (2026)

Carefully Structured Compression: Efficiently Managing StarCraft II Data
par: Ferenczi, Bryce, et autres
Publié: (2024)

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
par: Zimerman, Itamar, et autres
Publié: (2024)

Large Language Models Are Not Strong Abstract Reasoners
par: Gendron, Gaël, et autres
Publié: (2023)

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
par: Lan, Guangchen, et autres
Publié: (2025)

Avoiding Death through Fear Intrinsic Conditioning
par: Sanchez, Rodney, et autres
Publié: (2025)

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
par: Rath, Plawan Kumar, et autres
Publié: (2026)

BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks
par: Gandhi, Shubham, et autres
Publié: (2024)

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

D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning
par: Wang, Caroline, et autres
Publié: (2022)