Imagen de Portada

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chowdhury, Sanjoy, Manocha, Dinesh
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs
por: Chowdhury, Sanjoy, et al.
Publicado: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
por: Cheng, Stephen, et al.
Publicado: (2026)

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis
por: Dorbala, Vishnu Sashank, et al.
Publicado: (2024)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
por: Dai, Xinnan, et al.
Publicado: (2025)

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time
por: Chowdhury, Sanjoy, et al.
Publicado: (2024)

CASK: Core-Aware Selective KV Compression for Reasoning Traces
por: Kim, Buseong, et al.
Publicado: (2026)

EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception
por: Chowdhury, Sanjoy, et al.
Publicado: (2025)

Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes
por: Loxley, Peter N.
Publicado: (2024)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
por: Hammoud, Hasan Abed Al Kader, et al.
Publicado: (2025)

Uncovering the Latent Potential of Deep Intermediate Representations
por: Batra, Arnesh, et al.
Publicado: (2026)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
por: Li, Melody Zixuan, et al.
Publicado: (2025)

Navigating Potholes with Geometry-Aware Sharpness Minimization
por: Dufort-Labbé, Simon, et al.
Publicado: (2026)

Multi-LLM QA with Embodied Exploration
por: Patel, Bhrij, et al.
Publicado: (2024)

EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning
por: Seth, Ashish, et al.
Publicado: (2024)

The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
por: Musat, Tiberiu
Publicado: (2025)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
por: Patel, Bhrij, et al.
Publicado: (2024)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
por: Sun, Lihao, et al.
Publicado: (2026)

Genetics-Driven Personalized Disease Progression Model
por: Yang, Haoyu, et al.
Publicado: (2025)

Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
por: Yao, Laura, et al.
Publicado: (2026)

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
por: Huh, Gio, et al.
Publicado: (2025)

Generalizable Reasoning through Compositional Energy Minimization
por: Oarga, Alexandru, et al.
Publicado: (2025)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
por: Agarwal, Shivam, et al.
Publicado: (2025)

Learning Smooth Distance Functions via Queries
por: Kumar, Akash, et al.
Publicado: (2024)

Probing the Trajectories of Reasoning Traces in Large Language Models
por: Ballon, Marthe, et al.
Publicado: (2026)

Representation Stability in a Minimal Continual Learning Agent
por: Subramanian, Vishnu
Publicado: (2026)

Unsupervised Representation Learning - an Invariant Risk Minimization Perspective
por: Norman, Yotam, et al.
Publicado: (2025)

Layer by Layer: Uncovering Hidden Representations in Language Models
por: Skean, Oscar, et al.
Publicado: (2025)

The Geometry of Reasoning: Flowing Logics in Representation Space
por: Zhou, Yufa, et al.
Publicado: (2025)

Diagnosing Generalization Failures from Representational Geometry Markers
por: Chou, Chi-Ning, et al.
Publicado: (2026)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
por: Wang, Changsheng, et al.
Publicado: (2025)

In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations
por: Knauer, Ricardo, et al.
Publicado: (2026)

LLM DNA: Tracing Model Evolution via Functional Representations
por: Wu, Zhaomin, et al.
Publicado: (2025)

TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification
por: Anand, Nishit, et al.
Publicado: (2024)

SafeCoT: Improving VLM Safety with Minimal Reasoning
por: Ma, Jiachen, et al.
Publicado: (2025)

Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
por: Lippl, Samuel, et al.
Publicado: (2025)

Contrastive Representations for Temporal Reasoning
por: Ziarko, Alicja, et al.
Publicado: (2025)

The Geometry of Self-Verification in a Task-Specific Reasoning Model
por: Lee, Andrew, et al.
Publicado: (2025)

FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
por: Wen, Tian, et al.
Publicado: (2026)

Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
por: Song, Yeongwoo, et al.
Publicado: (2025)

Tracing Uncertainty in Language Model "Reasoning"
por: Grünefeld, Nils, et al.
Publicado: (2026)