28 citations · 60 across the 12 of their papers we have counts for
19 papers
Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation
Songyuan Sui, Srikanth Malla, Chiho Choi +1
Personalized large language models often require a complete adaptation state for each user. However, this paradigm scales poorly as the user population grows. We revisit this desig…
Steering Interference Reflects the Model's Defaults, Not the Behavior Directions
Srikanth Malla, Chiho Choi, Joon Hee Choi
Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activations, and adding that directio…
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists
Srikanth Malla, Chiho Choi, Joon Hee Choi
Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023), fine-tuning attacks (Qi et al., 2024), and activation-sp…
ADEPT: Adaptive Dynamic Early-Exit Process for Transformers
Sangmin Yoo, Srikanth Malla, Chiho Choi +2
The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have pr…
CAMILA: Context-Aware Masking for Image Editing with Language Alignment
Hyunseung Kim, Chiho Choi, Srikanth Malla +3
Text-guided image editing has been allowing users to transform and synthesize images through natural language instructions, offering considerable flexibility. However, most existin…
COPAL: Continual Pruning in Large Language Generative Models
Srikanth Malla, Joon Hee Choi, Chiho Choi
Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to…
CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping
Srikanth Malla, Yi-Ting Chen
Point cloud data plays an essential role in robotics and self-driving applications. Yet, annotating point cloud data is time-consuming and nontrivial while they enable learning dis…
DRAMA: Joint Risk Localization and Captioning in Driving
Srikanth Malla, Chiho Choi, Isht Dwivedi +2
Considering the functionality of situational awareness in safety-critical automation systems, the perception of risk in driving scenes and its explainability is of particular impor…
LOKI: Long Term and Key Intentions for Trajectory Prediction
Harshayu Girase, Haiming Gang, Srikanth Malla +4
Recent advances in trajectory prediction have shown that explicit reasoning about agents' intent is important to accurately forecast their motion. However, the current research act…
RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting
Jiachen Li, Fan Yang, Hengbo Ma +3
Motion forecasting plays a significant role in various domains (e.g., autonomous driving, human-robot interaction), which aims to predict future motion sequences given a set of his…
Shared Cross-Modal Trajectory Prediction for Autonomous Driving
Chiho Choi, Joon Hee Choi, Jiachen Li +1
Predicting future trajectories of traffic agents in highly interactive environments is an essential and challenging problem for the safe operation of autonomous driving systems. On…
Social-STAGE: Spatio-Temporal Multi-Modal Future Trajectory Forecast
Srikanth Malla, Chiho Choi, Behzad Dariush
This paper considers the problem of multi-modal future trajectory forecast with ranking. Here, multi-modality and ranking refer to the multiple plausible path predictions and the c…
SSP: Single Shot Future Trajectory Prediction
Isht Dwivedi, Srikanth Malla, Behzad Dariush +1
We propose a robust solution to future trajectory forecast, which can be practically applicable to autonomous agents in highly crowded environments. For this, three aspects are par…
Shared Cross-Modal Trajectory Prediction for Autonomous Driving
Chiho Choi, Joon Hee Choi, Srikanth Malla +1
Predicting future trajectories of traffic agents in highly interactive environments is an essential and challenging problem for the safe operation of autonomous driving systems. On…
TITAN: Future Forecast using Action Priors
Srikanth Malla, Behzad Dariush, Chiho Choi
We consider the problem of predicting the future trajectory of scene agents from egocentric views obtained from a moving platform. This problem is important in a variety of domains…
NEMO: Future Object Localization Using Noisy Ego Priors
Srikanth Malla, Isht Dwivedi, Behzad Dariush +1
Predicting the future trajectory of agents from visual observations is an important problem for realization of safe and effective navigation of autonomous systems in dynamic enviro…
DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning
Chiho Choi, Srikanth Malla, Abhishek Patil +1
We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in traffic…
The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes
Abhishek Patil, Srikanth Malla, Haiming Gang +1
3D multi-object detection and tracking are crucial for traffic scene understanding. However, the community pays less attention to these areas due to the lack of a standardized benc…
Semi-supervised Learning: Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection
Athma Narayanan, Yi-Ting Chen, Srikanth Malla
In this paper, we presented a preliminary study for tactical driver behavior detection from untrimmed naturalistic driving recordings. While supervised learning based detection is…