Imagen de Portada

Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yifan, Bi, Wei, Zhang, Kechi, Jin, Dongming, Fu, Jie, Jin, Zhi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
por: Zhang, Yifan, et al.
Publicado: (2025)

IntentCoding: Amplifying User Intent in Code Generation
por: Fang, Zheng, et al.
Publicado: (2026)

A Survey on Code Generation with LLM-based Agents
por: Dong, Yihong, et al.
Publicado: (2025)

Rethinking Regularization Methods for Knowledge Graph Completion
por: Li, Linyu, et al.
Publicado: (2025)

Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding
por: Li, Linyu, et al.
Publicado: (2025)

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
por: Tas, Omer Sahin, et al.
Publicado: (2024)

BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
por: Ding, Yifu, et al.
Publicado: (2026)

Residual Stream Duality in Modern Transformer Architectures
por: Zhang, Yifan
Publicado: (2026)

Discovering Interpretable Algorithms by Decompiling Transformers to RASP
por: Huang, Xinting, et al.
Publicado: (2026)

Discrete Neural Algorithmic Reasoning
por: Rodionov, Gleb, et al.
Publicado: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
por: Sun, Chung-En, et al.
Publicado: (2025)

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
por: IslamBouli, Beshr, et al.
Publicado: (2026)

Self-Infilling Code Generation
por: Zheng, Lin, et al.
Publicado: (2023)

Converting Transformers into DGNNs Form
por: Zhang, Jie, et al.
Publicado: (2025)

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
por: Dong, Yihong, et al.
Publicado: (2026)

Dataless Knowledge Fusion by Merging Weights of Language Models
por: Jin, Xisen, et al.
Publicado: (2022)

Extracting Rule-based Descriptions of Attention Features in Transformers
por: Friedman, Dan, et al.
Publicado: (2025)

DWTSumm: Discrete Wavelet Transform for Document Summarization
por: Salama, Rana, et al.
Publicado: (2026)

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
por: Tao, Yongding, et al.
Publicado: (2025)

Mechanistic Interpretability of Binary and Ternary Transformers
por: Li, Jason
Publicado: (2024)

Extracting Prompts by Inverting LLM Outputs
por: Zhang, Collin, et al.
Publicado: (2024)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
por: Zhang, Zhongwang, et al.
Publicado: (2025)

Massive Editing for Large Language Models via Meta Learning
por: Tan, Chenmien, et al.
Publicado: (2023)

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
por: Dong, Yihong, et al.
Publicado: (2025)

MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds
por: Jin, Xiaolong, et al.
Publicado: (2024)

Sparse Transformer with Local and Seasonal Adaptation for Multivariate Time Series Forecasting
por: Zhang, Yifan, et al.
Publicado: (2023)

Unified Lexical Representation for Interpretable Visual-Language Alignment
por: Li, Yifan, et al.
Publicado: (2024)

Model Assembly Learning with Heterogeneous Layer Weight Merging
por: Zhang, Yi-Kai, et al.
Publicado: (2025)

Learning to Interpret Weight Differences in Language Models
por: Goel, Avichal, et al.
Publicado: (2025)

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
por: Anagnostidis, Sotiris, et al.
Publicado: (2023)

Rethinking Repetition Problems of LLMs in Code Generation
por: Dong, Yihong, et al.
Publicado: (2025)

Transformers meet Neural Algorithmic Reasoners
por: Bounsi, Wilfried, et al.
Publicado: (2024)

The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations
por: Zhang, Long, et al.
Publicado: (2026)

GLM-5: from Vibe Coding to Agentic Engineering
por: GLM-5-Team, et al.
Publicado: (2026)

Learning Novel Transformer Architecture for Time-series Forecasting
por: Zhang, Juyuan, et al.
Publicado: (2025)

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
por: Wang, Haoxiang, et al.
Publicado: (2024)

Controlled LLM Decoding via Discrete Auto-regressive Biasing
por: Pynadath, Patrick, et al.
Publicado: (2025)

Mental Multi-class Classification on Social Media: Benchmarking Transformer Architectures against LSTM Models
por: Hasan, Khalid, et al.
Publicado: (2025)

Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code
por: Bao, Keqin, et al.
Publicado: (2025)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models
por: Garg, Ankur, et al.
Publicado: (2025)