Ranjay Krishna
~Ranjay_Krishna1
23
论文总数
11.5
年均投稿
平均评分
接收情况14/23
会议分布
ICLR
13
NeurIPS
6
COLM
3
ICML
1
发表论文 (23 篇)
202512 篇
5
Diffusion Models are Few-shot Learners for Dense Vision Tasks
ICLR 2025Rejected
4
Visual Representations inside the Language Model
COLM 2025Poster
4
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
COLM 2025Poster
4
Convergent Functions, Divergent Forms
NeurIPS 2025Poster
4
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
ICLR 2025Rejected
4
Language Model Preference Evaluation with Multiple Weak Evaluators
ICLR 2025Rejected
3
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
ICML 2025Poster
4
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
ICLR 2025Poster
3
Coarse Correspondences Boost 3D Spacetime Understanding in Multimodal Language Model
ICLR 2025withdrawn
4
SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
COLM 2025Poster
5
Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
ICLR 2025Spotlight
4
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
NeurIPS 2025Poster
202411 篇
3
EcoAssistant: Using LLM Assistant More Affordably and Accurately
ICLR 2024Rejected
3
Cultural and Linguistic Diversity Improves Visual Representations
ICLR 2024Rejected
4
Optimizing Interpersonal Communication by Simulating Audiences with Large Language Models
ICLR 2024Rejected
4
Selective Visual Representations Improve Convergence and Generalization for Embodied AI
ICLR 2024Spotlight
3
Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
ICLR 2024Poster
4
LeetPrompt: Leveraging Collective Human Intelligence to Study LLMs
ICLR 2024withdrawn
4
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
NeurIPS 2024Poster
4
MIMIC: Masked Image Modeling with Image Correspondences
ICLR 2024withdrawn
4
Multilingual Diversity Improves Vision-Language Representations
NeurIPS 2024Spotlight
4
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
NeurIPS 2024Poster
4
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
NeurIPS 2024Poster