14 papers
Geometrically Principled Randomized Optimization for Efficient LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
Low-rank gradient optimization for large language models is currently divided into two categories: structured methods that rigorously identify subspaces, and randomized approaches…
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey +8
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, be…
PinPoint: Prompting with Informative Interior Points
Pouya Sadeghi, Shawn He, Pedro Pablo Guerrero Vela +3
Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask gener…
Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
Dmytro Klepachevskyi, Alexander Wong, Sirisha Rambhatla +1
Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance…
Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation
Jerrin Bright, Zhibo Wang, Dmytro Klepachevskyi +4
We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, wh…
SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
Training large language models (LLMs) is highly resource-intensive due to their massive number of parameters and the overhead of optimizer states. While recent work has aimed to re…