Vikas Chandra
34 papers · 2021–2026 · 12 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🌍 Conference Polyglot (12) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9)
🌈
Renaissance Researcher
(6)
🌍
Conference Polyglot
(12)
🤝
Dynamic Duo
(12)
🔥
Unstoppable
(5)
💎
Century Club
(33)
⚡
Prolific Year
(9)
🗃️
Keyword Collector
(128)
Conferences
CVPR (7)
ACL (6)
ICML (6)
ICLR (3)
ECCV (2)
EMNLP (2)
INTERSPEECH (2)
NAACL (2)
AAAI (1)
AISTATS (1)
AUTOML (1)
ICCV (1)
Top co-authors
Keywords
knowledge distillation
(5)
model compression
(5)
neural architecture search
(5)
vision transformer
(3)
image classification
(3)
semantic segmentation
(2)
weight sharing
(2)
on-device inference
(2)
large language model
(2)
supernet training
(2)
zero-shot transfer
(2)
object detection
(2)
automatic speech recognition
(2)
segment anything model
(2)
domain adaptation
(1)
variational inference
(1)
adversarial robustness
(1)
model quantization
(1)
semi-supervised learning
(1)
image segmentation
(1)
Papers
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
ACL 2026
Efficient Track Anything
ICCV 2025
Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
NAACL 2025
EdgeTAM: On-Device Track Anything Model
CVPR 2025
Self-Vocabularizing Training for Neural Machine Translation
NAACL 2025
AutoMixer: Checkpoint Artifacts as Automatic Data Mixers
ACL 2025
SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
AISTATS 2025
Agent-as-a-Judge: Evaluate Agents with Agents
ICML 2025
SpinQuant: LLM Quantization with Learned Rotations
ICLR 2025
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
ICML 2025
Target-Aware Language Modeling via Granular Data Sampling
EMNLP 2024
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
ACL 2024
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
ACL 2024
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
CVPR 2024
Taming Mode Collapse in Score Distillation for Text-to-3D Generation
CVPR 2024
MVDiffHD: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
ECCV 2024
CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
ECCV 2024
Scaling Parameter-Constrained Language Models with Quality Data
EMNLP 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Fast Point Cloud Generation With Straight Flows
CVPR 2023
Revisiting Sample Size Determination in Natural Language Understanding
ACL 2023
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses
ACL 2023
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
CVPR 2022
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
ICML 2022
Streaming parallel transducer beam search with fast slow cascaded encoders
INTERSPEECH 2022
ScaleNAS: Multi-Path One-Shot NAS for Scale-Aware High-Resolution Representation
AUTOML 2022
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
ICLR 2022
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
CVPR 2021
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
CVPR 2021
Collaborative Training of Acoustic Encoders for Speech Recognition
INTERSPEECH 2021
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
ICML 2021
AlphaNet: Improved Training of Supernets with Alpha-Divergence
ICML 2021
CPT: Efficient Deep Neural Network Training via Cyclic Precision
ICLR 2021
NASGEM: Neural Architecture Search via Graph Embedding Method
AAAI 2021