Shivam Raval

Orcid: 0000-0002-3742-8209

According to our database1, Shivam Raval authored at least 20 papers between 2018 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering.
CoRR, May, 2026

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models.
CoRR, May, 2026

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers.
CoRR, April, 2026

Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering.
CoRR, April, 2026

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models.
CoRR, April, 2026

DreamReader: An Interpretability Toolkit for Text-to-Image Models.
CoRR, March, 2026

Curveball Steering: The Right Direction To Steer Isn't Always Linear.
CoRR, March, 2026

MoE Lens - An Expert Is All You Need.
CoRR, March, 2026

Narrow fine-tuning erodes safety alignment in vision-language agents.
CoRR, February, 2026

Spectral Superposition: A Theory of Feature Geometry.
CoRR, February, 2026

Latent manipulator: using concept-guided embedding manipulation to steer embedding visualizations.
Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems, 2026

2025
Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests.
CoRR, October, 2025

Towards mitigating information leakage when evaluating safety monitors.
CoRR, September, 2025

Caught in the Act: a mechanistic approach to detecting deception.
CoRR, August, 2025

2024
Designing a Dashboard for Transparency and Control of Conversational AI.
CoRR, 2024

Hypertrix: An indicatrix for high-dimensional visualizations.
Proceedings of the IEEE Visualization and Visual Analytics, 2024

2023
Explain-and-Test: An Interactive Machine Learning Framework for Exploring Text Embeddings.
Proceedings of the 2023 IEEE Visualization and Visual Analytics (VIS), 2023

2021
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2021, 2021

Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2021, 2021

2018
Performance Analysis of Improved Energy Detection in Full Duplex Non-Time-Slotted Cognitive Radio.
Proceedings of the IEEE International Conference on Advanced Networks and Telecommunications Systems, 2018


  Loading...