AI & ML interests
LLM, VLM, Inference Optimization, AI4Math, Watermarking
Recent Activity
Papers
CPPO: Contrastive Perception for Vision Language Policy Optimization
From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
-
Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
Paper • 2509.06266 • Published • 12 -
From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
Paper • 2512.05277 • Published • 6 -
vbdai/CPPO-3B
4B • Updated • 26 • 2 -
vbdai/CPPO-7B
8B • Updated • 23 • 1
-
LaWa: Using Latent Space for In-Generation Image Watermarking
Paper • 2408.05868 • Published • 4 -
AMUSE: Adaptive Multi-Segment Encoding for Dataset Watermarking
Paper • 2403.05628 • Published -
Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking
Paper • 2409.00314 • Published • 3 -
Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers
Paper • 2412.12563 • Published • 2
-
Evaluating LLM Reasoning in the Operations Research Domain with ORQA
Paper • 2412.17874 • Published • 2 -
EvoCut: Strengthening Integer Programs via Evolution-Guided Language Models
Paper • 2508.11850 • Published • 3 -
Discrete Optimization of Min-Max Violation and its Applications Across Computational Sciences
Paper • 2508.13437 • Published • 1 -
SMARTAPS: Tool-augmented LLMs for Operations Management
Paper • 2507.17927 • Published • 1
-
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
Paper • 2503.02175 • Published • 4 -
CASP: Compression of Large Multimodal Models Based on Attention Sparsity
Paper • 2503.05936 • Published • 3 -
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Paper • 2110.10343 • Published • 1 -
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
Paper • 2203.00748 • Published • 1
-
Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
Paper • 2509.06266 • Published • 12 -
From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
Paper • 2512.05277 • Published • 6 -
vbdai/CPPO-3B
4B • Updated • 26 • 2 -
vbdai/CPPO-7B
8B • Updated • 23 • 1
-
Evaluating LLM Reasoning in the Operations Research Domain with ORQA
Paper • 2412.17874 • Published • 2 -
EvoCut: Strengthening Integer Programs via Evolution-Guided Language Models
Paper • 2508.11850 • Published • 3 -
Discrete Optimization of Min-Max Violation and its Applications Across Computational Sciences
Paper • 2508.13437 • Published • 1 -
SMARTAPS: Tool-augmented LLMs for Operations Management
Paper • 2507.17927 • Published • 1
-
LaWa: Using Latent Space for In-Generation Image Watermarking
Paper • 2408.05868 • Published • 4 -
AMUSE: Adaptive Multi-Segment Encoding for Dataset Watermarking
Paper • 2403.05628 • Published -
Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking
Paper • 2409.00314 • Published • 3 -
Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers
Paper • 2412.12563 • Published • 2
-
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
Paper • 2503.02175 • Published • 4 -
CASP: Compression of Large Multimodal Models Based on Attention Sparsity
Paper • 2503.05936 • Published • 3 -
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Paper • 2110.10343 • Published • 1 -
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
Paper • 2203.00748 • Published • 1