Sachin Goyal
9 papers · 2020–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(30)
🗃️
Keyword Collector
(50)
Venues
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(6)
Core AI
(5)
Learning Types · Machine Learning
(5)
Optimization & Theory
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Application Areas
(3)
Computer Vision
(2)
Core Methods
(2)
Generation
(2)
Learning Paradigms · Artificial Intelligence
(2)
Learning Types · Deep Learning
(2)
Analysis
(1)
Learning Paradigms · Machine Learning
(1)
Keywords
vision-language model
(3)
scaling law
(2)
data filtering
(2)
zero-shot learning
(2)
deep learning
(1)
question answering
(1)
entropy minimization
(1)
model behavior
(1)
anomaly detection
(1)
prompt learning
(1)
visual representation
(1)
out-of-distribution generalization
(1)
pretraining
(1)
distribution shift
(1)
language model
(1)
test-time adaptation
(1)
low-dimensional manifold
(1)
domain adaptation
(1)
instruction fine-tuning
(1)
contrastive learning
(1)
Papers
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
ICLR 2025
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
ICLR 2025
Overtrained Language Models Are Harder to Fine-Tune
ICML 2025
Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic
CVPR 2024
Think before you speak: Training Language Models With Pause Tokens
ICLR 2024
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
ICLR 2024
Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models
CVPR 2023
Test Time Adaptation via Conjugate Pseudo-labels
NeurIPS 2022
DROCC: Deep Robust One-Class Classification
ICML 2020