JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Paper • 2610.00722 • Published • 3
AI & ML interests
We develop computational models for language processing that take into account the rich situational and communicative context and build embodied AI agents that can communicate with humans in language.
Recent Activity
View all activity
cozzyde
authored a
paper 23 days ago
cozzyde
submitted a
paper to Daily Papers 23 days ago
Zekun
authored 5
papers about 1 month ago
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
Paper • 2305.12544 • Published • 2
Trust Region Continual Learning as an Implicit Meta-Learner
Paper • 2602.02417 • Published
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
Paper • 2605.07076 • Published • 2
Hierarchical Semantic Retrieval with Cobweb
Paper • 2510.02539 • Published
Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
Paper • 2509.23593 • Published • 2
cozzyde
authored a
paper about 1 month ago
cozzyde
submitted a
paper to Daily Papers about 1 month ago
6kplus
authored 6
papers 3 months ago
The Mechanistic Emergence of Symbol Grounding in Language Models
Paper • 2510.13796 • Published
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
Paper • 2605.14269 • Published • 7
Planning with Sketch-Guided Verification for Physics-Aware Video Generation
Paper • 2511.17450 • Published • 4
DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences
Paper • 2406.03008 • Published
Inversion-Free Image Editing with Natural Language
Paper • 2312.04965 • Published • 2
CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
Paper • 2310.13165 • Published
cozzyde
submitted a
paper to Daily Papers 4 months ago
cozzyde
authored 3
papers 4 months ago
From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
Paper • 2310.18364 • Published • 1
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities
Paper • 2410.17385 • Published • 1
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
Paper • 2606.24893 • Published • 9
sihanxu
authored a
paper 5 months ago