Kai Bishop

kaibishop's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 1 day ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

Paper • 2609.35291 • Published 19 days ago • 26

Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score

Paper • 2610.03825 • Published 15 days ago • 5

upvoted 4 papers 2 days ago

InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators

Paper • 2610.13944 • Published 8 days ago • 25

Learning Representations to Guide Pixel Diffusion Transformers

Paper • 2610.12978 • Published 8 days ago • 31

ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning

Paper • 2610.13316 • Published 8 days ago • 7

EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents

Paper • 2610.13021 • Published 8 days ago • 74

upvoted a paper 5 days ago

When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents

Paper • 2609.32520 • Published 21 days ago • 25

upvoted a paper 6 days ago

Building Rome from a Single Image

Paper • 2610.08790 • Published 11 days ago • 18

upvoted a paper 8 days ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 13 days ago • 174

upvoted a paper 9 days ago

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

Paper • 2610.02179 • Published 16 days ago • 21

upvoted 3 papers 10 days ago

Scaling and Distilling Text Embeddings for Better Diffusibility

Paper • 2610.01016 • Published 16 days ago • 58

Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces

Paper • 2609.40362 • Published 17 days ago • 40

Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts

Paper • 2610.00314 • Published 18 days ago • 103

upvoted 2 papers 11 days ago

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published 17 days ago • 47

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 17 days ago • 276

upvoted 2 papers 13 days ago

AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation

Paper • 2609.35530 • Published 19 days ago • 23

Chinese-Jev: Bringing System One Model to Chinese-Language Tasks

Paper • 2609.36965 • Published 18 days ago • 26

upvoted 3 papers 14 days ago

Reasoning with Image Generation

Paper • 2609.16409 • Published Sep 14 • 25

Adversarial Training for Pixel Diffusion

Paper • 2609.38170 • Published 18 days ago • 22

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Paper • 2609.37775 • Published 18 days ago • 26