Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Paper ā¢ 2610.21601 ā¢ Published ā¢ 451
liweiqing
lwq
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation authored a paper 9 days ago
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability authored a paper 9 days ago
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache
Transfer and Load-Aware SchedulingOrganizations
upvoted a paper about 18 hours ago
authored 5
papers 9 days ago
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
Paper ā¢ 2610.08448 ā¢ Published ā¢ 213
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
Paper ā¢ 2504.03775 ā¢ Published
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Paper ā¢ 2608.26730 ā¢ Published ā¢ 154
Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval
Paper ā¢ 2603.16455 ā¢ Published
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization
Paper ā¢ 2601.11200 ā¢ Published
upvoted a paper 10 days ago
upvoted a paper about 1 month ago
upvoted a paper 5 months ago
liked a
model 10 months ago
If possible, Iād really appreciate it if you could share the related technical report.
2
#1 opened 11 months ago
by 
gangsu
liked 3
Spaces 11 months ago
liked a
model 12 months ago
updated 2
models 12 months ago