2 citations · 9 across the 8 of their papers we have counts for
8 papers
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma +6
We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master…
Efficient Model Development through Fine-tuning Transfer
Pin-Jie Lin, Rishab Balasubramanian, Fengyuan Liu +2
Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or langua…
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli +3
We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capt…
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
Zeyu Zhang, Yi Su, Hui Yuan +5
Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make stron…
Adversarial Attacks on Online Learning to Rank with Stochastic Click Models
Zichen Wang, Rishab Balasubramanian, Hui Yuan +3
We propose the first study of adversarial attacks on online learning to rank. The goal of the adversary is to misguide the online learning to rank algorithm to place the target ite…
Contrastive Learning for Object Detection
Rishab Balasubramanian, Kunal Rathore
Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negat…
Contrastive Learning for OOD in Object detection
Rishab Balasubramanian, Rupashree Dey, Kunal Rathore
Contrastive learning is commonly applied to self-supervised learning, and has been shown to outperform traditional approaches such as the triplet loss and N-pair loss. However, the…
Risk-Aware Submodular Optimization for Multi-objective Travelling Salesperson Problem
Rishab Balasubramanian, Lifeng Zhou, Pratap Tokekar +1
We introduce a risk-aware multi-objective Traveling Salesperson Problem (TSP) variant, where the robot tour cost and tour reward have to be optimized simultaneously. The robot obta…