8 papers · 1 filter
Understanding and Exploiting Anisotropy in Post-Training
Samyak Jha, Harshvardhan Saini, Yizhen Liao +2
LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective. Frequency-weig…
Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
Yiming Tang, Harshvardhan Saini, Samyak Jha +3
Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability, essential both for the scien…
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
Jing Yu Lim, Rushi Shah, Zarif Ikram +4
Diffusion world models have recently become competitive for online model-based reinforcement learning, but current approaches expose a tension: pixel diffusion is effective but com…
Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization
Wenhao Zhao, Qiran Zou, Zhouhan Lin +1
Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a…
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
Harshvardhan Saini, Yiming Tang, Dianbo Liu
Controlling emergent behavioral personas (e.g., sycophancy, hallucination) in Large Language Models (LLMs) is critical for AI safety, yet remains a persistent challenge. Existing s…
A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
Yiming Tang, Harshvardhan Saini, Zhaoqian Yao +6
As AI models achieve remarkable capabilities across diverse domains, understanding what representations they learn and how they encode concepts has become increasingly important fo…
How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders
Yiming Tang, Abhijeet Sinha, Dianbo Liu
Although recent generative models are remarkably capable of producing instruction-following and realistic outputs, they remain prone to notable physical plausibility failures. Thou…
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Tianyi Zhang, Yu Cao, Dianbo Liu
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos. While previous studies have…