No article text was recorded for this version.
latent computation tokens
Version 1 of 134 papers50 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
- Blog: Expanding Computation Spaces of LLMs at Inference Time
- Blog: Implicit Reasoning in Large Language Models: A Comprehensive Survey
- Blog: (How) Do reasoning models reason?
- Blog: Understanding Transformer Reasoning Capabilities via Graph Algorithms
- Blog: Latent Chain-of-Thought Improves Structured-Data Transformers
- Blog: The Impossibility of Inverse Permutation Learning in Transformer Models
- Blog: Disentangling Memory and Reasoning Ability in Large Language Models
- Blog: Let’s Think Dot by Dot: Hidden computation in transformer language models
- Blog: Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent Reasoning
- Blog: Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
- Blog: Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
- Blog: Multi-label Sequential Sentence Classification via Large Language Model
- Blog: Think before you speak: Training Language Models With Pause Tokens
- Blog: Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
- Blog: A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
- Blog: Do Language Models Plan Ahead for Future Tokens?
- Blog: Vision-aligned Latent Reasoning for Multi-modal Large Language Model
- Blog: On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
- Blog: Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
- Blog: Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction
- Blog: PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
- Blog: Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
- Blog: Latent Collaboration in Multi-Agent Systems
- Blog: Replacing Linguists with Dummies: A Serious Need for Trivial Baselines in Multi-Task Neural Machine Translation
- Blog: Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
- Blog: Speedrunning Tabular Foundation Model Pretraining
- Blog: AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
- Blog: Interpreting the Latent Structure of Operator Precedence in Language Models
- Blog: TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
- Blog: Semformer: Transformer Language Models with Semantic Planning
- Blog: On the Power of Context-Enhanced Learning in LLMs
- Blog: Analysing Mathematical Reasoning Abilities of Neural Models
- Blog: MoDr: Mixture-of-Depth-Recurrent Transformers for Test-Time Reasoning
History & citation
Current · Permanent link
- Expanding Transformer Expressivity with Computational Filler Tokens merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_latent_computation_tokens_47ef1001,
title = {latent computation tokens},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/latent-computation-tokens/rdr_47ef10012943433d9d6d65f971279f53},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_latent_computation_tokens_47ef1001_v1,
title = {latent computation tokens},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/latent-computation-tokens/rdr_47ef10012943433d9d6d65f971279f53/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}