rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
Omni-rrm: Advancing omni reward modeling via automatic rubric-grounded preference synthesis.CoRR, abs/2602.00846
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
EarlyTom is a training-free early token compression method inside the vision encoder with decoupled spatial selection that reduces TTFT up to 2.65x and FLOPs 61% on LLaVA-OneVision-7B while keeping accuracy comparable to full tokens.
RLR³ extends RLVR to criterion-level rubric verification via dual execution paths, minimal exposure masking, hierarchical aggregation, and saturation mitigation, delivering 4.7-point gains over base on 15 benchmarks with Qwen3-VL-30B-A3B.
A literature synthesis that organizes post-training reasoning data research around data objects, usefulness factors, construction methods, and scaling behaviors to create an attribution framework.
citing papers explorer
-
Visual Preference Optimization with Rubric Rewards
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
-
EarlyTom: Early Token Compression Completes Fast Video Understanding
EarlyTom is a training-free early token compression method inside the vision encoder with decoupled spatial selection that reduces TTFT up to 2.65x and FLOPs 61% on LLaVA-OneVision-7B while keeping accuracy comparable to full tokens.
-
Reinforcement Learning with Robust Rubric Rewards
RLR³ extends RLVR to criterion-level rubric verification via dual execution paths, minimal exposure masking, hierarchical aggregation, and saturation mitigation, delivering 4.7-point gains over base on 15 benchmarks with Qwen3-VL-30B-A3B.
-
A Primer in Post-Training Reasoning Data: What We Know About How It Works
A literature synthesis that organizes post-training reasoning data research around data objects, usefulness factors, construction methods, and scaling behaviors to create an attribution framework.