Jay
JayXDev
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
Meta Context Engineering via Agentic Skill Evolution upvoted a paper about 9 hours ago
Bayesian Model Merging upvoted a paper about 9 hours ago
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-ExpertsOrganizations
None yet
Training-Finetune
-
Normalized Low-Rank Adaptation
Paper • 2608.31036 • Published • 55 -
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
Paper • 2604.18556 • Published • 19 -
Model Compression with Exact Budget Constraints via Riemannian Manifolds
Paper • 2605.00649 • Published • 7
Trading
-
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 143 -
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Paper • 2609.17632 • Published • 39 -
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 257
SelfEvolving
-
EvoX: Meta-Evolution for Automated Discovery
Paper • 2602.23413 • Published • 2 -
CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation
Paper • 2502.10802 • Published -
Bilevel Autoresearch: Meta-Autoresearching Itself
Paper • 2603.23420 • Published • 2 -
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Paper • 2608.23283 • Published • 210
Julia
ML-Training
Training-Finetune
-
Normalized Low-Rank Adaptation
Paper • 2608.31036 • Published • 55 -
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
Paper • 2604.18556 • Published • 19 -
Model Compression with Exact Budget Constraints via Riemannian Manifolds
Paper • 2605.00649 • Published • 7
SearchCrawlResearch
Trading
-
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 143 -
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Paper • 2609.17632 • Published • 39 -
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 257
LLM-Architectures
SelfEvolving
-
EvoX: Meta-Evolution for Automated Discovery
Paper • 2602.23413 • Published • 2 -
CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation
Paper • 2502.10802 • Published -
Bilevel Autoresearch: Meta-Autoresearching Itself
Paper • 2603.23420 • Published • 2 -
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Paper • 2608.23283 • Published • 210
2026-Local-Coders