Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
Paper • 2610.09411 • Published • 2
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data upvoted a paper 2 days ago
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents upvoted a paper 2 days ago
Agent Plasticity: Measuring Self-Improvement Through ExperienceOrganizations
None yet
upvoted 9
papers 2 days ago
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
Paper • 2610.09484 • Published • 28
Agent Plasticity: Measuring Self-Improvement Through Experience
Paper • 2610.08902 • Published • 6
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Paper • 2609.36322 • Published • 119
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
Paper • 2610.01892 • Published • 38
Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling
Paper • 2609.36529 • Published • 38
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 111
Decentralized Multi-Agent Systems with Shared Context
Paper • 2606.10662 • Published • 5
RoboJEPA: Scaling Robotic Latent World Models
Paper • 2610.10515 • Published • 6
upvoted 4
papers 3 days ago
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
Paper • 2610.08966 • Published • 26
Level-of-Token Diffusion
Paper • 2610.05816 • Published • 1
VERA: Scaling Verifiable Environments for Agentic co-Evolution
Paper • 2610.05923 • Published • 2
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
Paper • 2609.39050 • Published • 21
upvoted a paper 4 days ago
upvoted 6
papers 5 days ago
ALoDLM: Adaptively Looped Diffusion Language Models
Paper • 2610.04198 • Published • 79
Harness-Aware Distillation for Small Language Model Agents
Paper • 2610.02858 • Published • 16
Base Models Can Reason By Taking a Cue From Training Data
Paper • 2610.06851 • Published • 28
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Paper • 2610.06805 • Published • 1
Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
Paper • 2608.03893 • Published • 2
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model
Paper • 2609.18323 • Published • 121