JasperHaozhe/RationalRewards-Both-Demo
770k • Updated • 23
Haozhe Wang
JasperHaozhe
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation updated a collection 2 days ago
SearchGen updated a collection 2 days ago
SearchGenOrganizations
JasperHaozhe/qw3-4b-hicra-ckpt60
Updated • 1
JasperHaozhe/qw3-4B-base-hipo-ckpts
Updated
JasperHaozhe/qw3-4B-ins-hipo
4B • Updated • 2
JasperHaozhe/qw3-4B-ins-cliphigh-baseline
4B • Updated • 2
JasperHaozhe/qw3_4b_base_hipo
4B • Updated • 1
JasperHaozhe/qw3_4b_cliphigh_baseline
4B • Updated • 2
JasperHaozhe/qw25_7b_hipo
8B • Updated • 4
JasperHaozhe/qw25_7b_cliphigh_baseline
8B • Updated • 1
JasperHaozhe/qw25-32B-writer-v1-20K
33B • Updated • 2 • 1
JasperHaozhe/qw3writer-baseline
8B • Updated • 1
JasperHaozhe/qw3-4b-base-best
4B • Updated
JasperHaozhe/qw3-4b-base-baseline
4B • Updated
JasperHaozhe/qw3-4b-ins-planner-step256
Updated
JasperHaozhe/qw3-4b-base-planner-step292
Updated
JasperHaozhe/qw3writer_baseline_280
8B • Updated
JasperHaozhe/llama3writer_v4_819
Updated
JasperHaozhe/PixelReasoner-RL-v1.1
Updated
JasperHaozhe/VL-Reasoner-72B-v2
Updated