Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
Fuente:
arXiv
Saved in:
| Main Authors: | Singh, Simardeep, Chopra, Paras |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay
by: Baghel, Ashish, et al.
Published: (2026)
by: Baghel, Ashish, et al.
Published: (2026)
From Teacher to Student: Tracking Memorization Through Model Distillation
by: Singh, Simardeep
Published: (2025)
by: Singh, Simardeep
Published: (2025)
Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
by: Sharma, Aman, et al.
Published: (2025)
by: Sharma, Aman, et al.
Published: (2025)
Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts
by: Trehan, Dhruv, et al.
Published: (2026)
by: Trehan, Dhruv, et al.
Published: (2026)
The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
by: Sharma, Aman, et al.
Published: (2025)
by: Sharma, Aman, et al.
Published: (2025)
Discovering Reinforcement Learning Interfaces with Large Language Models
by: Jaswal, Akshat Singh, et al.
Published: (2026)
by: Jaswal, Akshat Singh, et al.
Published: (2026)
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
by: Sharma, Aman, et al.
Published: (2026)
by: Sharma, Aman, et al.
Published: (2026)
Hybrid Neural World Models
by: Lakshmanan, Pranav, et al.
Published: (2026)
by: Lakshmanan, Pranav, et al.
Published: (2026)
Building Interpretable Models for Moral Decision-Making
by: Goel, Mayank, et al.
Published: (2026)
by: Goel, Mayank, et al.
Published: (2026)
METIS: Mentoring Engine for Thoughtful Inquiry & Solutions
by: Kumar, Abhinav Rajeev, et al.
Published: (2026)
by: Kumar, Abhinav Rajeev, et al.
Published: (2026)
Do GFlowNets Transfer? Case Study on the Game of 24/42
by: Gupta, Adesh, et al.
Published: (2025)
by: Gupta, Adesh, et al.
Published: (2025)
LLM-Empowered Representation Learning for Emerging Item Recommendation
by: Zhang, Ziying, et al.
Published: (2025)
by: Zhang, Ziying, et al.
Published: (2025)
Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
by: Kuhar, Sachit, et al.
Published: (2023)
by: Kuhar, Sachit, et al.
Published: (2023)
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
by: Wei, Chen, et al.
Published: (2025)
by: Wei, Chen, et al.
Published: (2025)
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
by: Elbadry, Rania, et al.
Published: (2026)
by: Elbadry, Rania, et al.
Published: (2026)
A Mechanistic Investigation of Supervised Fine Tuning
by: Chopra, Ruhaan
Published: (2026)
by: Chopra, Ruhaan
Published: (2026)
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
by: Bjare, Mathias Rose, et al.
Published: (2025)
by: Bjare, Mathias Rose, et al.
Published: (2025)
Evaluating Human and Machine Confidence in Phishing Email Detection: A Comparative Study
by: Jain, Paras, et al.
Published: (2026)
by: Jain, Paras, et al.
Published: (2026)
Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
by: Chopra, Shivang, et al.
Published: (2023)
by: Chopra, Shivang, et al.
Published: (2023)
Large Population Models
by: Chopra, Ayush
Published: (2025)
by: Chopra, Ayush
Published: (2025)
The Representational Geometry of Number
by: Hu, Zhimin, et al.
Published: (2026)
by: Hu, Zhimin, et al.
Published: (2026)
TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns
by: Wang, Zhongbo, et al.
Published: (2026)
by: Wang, Zhongbo, et al.
Published: (2026)
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
by: Sun, Lihao, et al.
Published: (2026)
by: Sun, Lihao, et al.
Published: (2026)
Emergent Ordinal Geometry in Transformers Trained on Local Comparisons
by: Singh, Nishit
Published: (2026)
by: Singh, Nishit
Published: (2026)
Humanline: Online Alignment as Perceptual Loss
by: Liu, Sijia, et al.
Published: (2025)
by: Liu, Sijia, et al.
Published: (2025)
LangNav: Language as a Perceptual Representation for Navigation
by: Pan, Bowen, et al.
Published: (2023)
by: Pan, Bowen, et al.
Published: (2023)
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
by: Oh, Changdae, et al.
Published: (2026)
by: Oh, Changdae, et al.
Published: (2026)
Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
by: Du, Pengfei
Published: (2026)
by: Du, Pengfei
Published: (2026)
Human and AI Perceptual Differences in Image Classification Errors
by: Liu, Minghao, et al.
Published: (2023)
by: Liu, Minghao, et al.
Published: (2023)
LLM-Driven Auto Configuration for Transient IoT Device Collaboration
by: Shastri, Hetvi, et al.
Published: (2025)
by: Shastri, Hetvi, et al.
Published: (2025)
Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD
by: Gong, Shengjie, et al.
Published: (2026)
by: Gong, Shengjie, et al.
Published: (2026)
Towards Unifying Perceptual Reasoning and Logical Reasoning
by: Kido, Hiroyuki
Published: (2022)
by: Kido, Hiroyuki
Published: (2022)
Geometry over Density: Few-Shot Cross-Domain OOD Detection
by: Li, Shawn, et al.
Published: (2026)
by: Li, Shawn, et al.
Published: (2026)
Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation
by: Chopra, Shivang, et al.
Published: (2024)
by: Chopra, Shivang, et al.
Published: (2024)
CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection
by: Aïmeur, Esma, et al.
Published: (2026)
by: Aïmeur, Esma, et al.
Published: (2026)
Causality Guided Representation Learning for Cross-Style Hate Speech Detection
by: Zhao, Chengshuai, et al.
Published: (2025)
by: Zhao, Chengshuai, et al.
Published: (2025)
Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
by: Zhong, Yisheng, et al.
Published: (2026)
by: Zhong, Yisheng, et al.
Published: (2026)
DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring
by: Wu, Zhenqi, et al.
Published: (2025)
by: Wu, Zhenqi, et al.
Published: (2025)
A Cortically Inspired Architecture for Modular Perceptual AI
by: Luthra, Prerna
Published: (2026)
by: Luthra, Prerna
Published: (2026)
Perceptual Asymmetry Between Hue Categories: Evidence from Human Color Categorization
by: Kadyrgali, Elnara, et al.
Published: (2026)
by: Kadyrgali, Elnara, et al.
Published: (2026)
Similar Items
-
See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay
by: Baghel, Ashish, et al.
Published: (2026) -
From Teacher to Student: Tracking Memorization Through Model Distillation
by: Singh, Simardeep
Published: (2025) -
Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
by: Sharma, Aman, et al.
Published: (2025) -
Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts
by: Trehan, Dhruv, et al.
Published: (2026) -
The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
by: Sharma, Aman, et al.
Published: (2025)