JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Paper • 2608.25593 • Published • 107
Heng Chang
hchang95
AI & ML interests
Trustworthy ML, Graph Representation Learning
Recent Activity
authored a paper 2 days ago
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution authored a paper 2 days ago
Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models authored a paper 2 days ago
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward MechanismOrganizations
None yet
authored 6
papers 2 days ago
Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models
Paper • 2601.11342 • Published
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
Paper • 2506.08691 • Published
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
Paper • 2606.01779 • Published • 7
On the Limitations and Prospects of Machine Unlearning for Generative AI
Paper • 2408.00376 • Published
A-MapReduce: Executing Wide Search via Agentic MapReduce
Paper • 2602.01331 • Published • 1
upvoted a paper 2 days ago
authored 9
papers 5 months ago
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
Paper • 2304.02419 • Published
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
Paper • 2405.20202 • Published
Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
Paper • 2405.15304 • Published
Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering
Paper • 2402.14320 • Published
G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation
Paper • 2502.12586 • Published
GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning
Paper • 2507.23581 • Published
Context Compression via Explicit Information Transmission
Paper • 2602.03784 • Published • 16
TodoEvolve: Learning to Architect Agent Planning Systems
Paper • 2602.07839 • Published • 6
LoopRPT: Reinforcement Pre-Training for Looped Language Models
Paper • 2603.19714 • Published • 15
upvoted a paper 5 months ago
upvoted a paper over 1 year ago
liked a
Space over 1 year ago
upvoted an article over 1 year ago
Article
MLA: Redefining KV-Cache Through Low-Rank Projections and On-Demand Decompression
NormalUhr
• • 24