ProbePO: Sparse Probes, Redistributed Credit for Critic-Free LLM Reinforcement Learning
Paper • 2610.24515 • Published • 3
🤝 Open to Collab
Hanqing Zeng
zimplex
AI & ML interests
None yet
Recent Activity
authored a paper 5 days ago
ProbePO: Sparse Probes, Redistributed Credit for Critic-Free LLM Reinforcement Learning updated a dataset 5 days ago
zimplex/hrcf-big-results published a dataset 5 days ago
zimplex/hrcf-big-resultsOrganizations
authored a
paper 5 days ago
updated a
dataset 5 days ago
published a
dataset 5 days ago
updated a
model 8 days ago
published a
model 8 days ago
upvoted a paper 9 days ago
updated a
model 10 days ago
published a
model 10 days ago
authored 5
papers 16 days ago
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Paper • 2606.20554 • Published
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Paper • 2610.04918 • Published
Self-Evolving Memory for Generative Recommendation
Paper • 2609.15598 • Published
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Paper • 2608.05446 • Published • 1
Verifiable Reasoning for LLM-based Generative Recommendation
Paper • 2603.07725 • Published
published a
model 24 days ago
updated a
model 24 days ago
published a
model 25 days ago
updated a
model 25 days ago
published a
model 25 days ago
updated a
model 25 days ago
published a
model 25 days ago