DDE models class-wise positive feature Gaussians and negative label distributions to boost ID accuracy and OOD detection in zero-shot noisy TTA, reporting 3.70% harmonic mean gain and 6.20% FPR95 drop on ImageNet.
Ammkd: Adaptive multimodal multi-teacher distillation for lightweight vision-language models.arXiv preprint arXiv:2509.00039, 2025
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
TOPD improves on-policy distillation for LLM reasoning by using near-future guidance to identify divergent states, raising average accuracy from 47.8% to 52.2% on math benchmarks including AIME24 and AIME25.
Rock Tokens in on-policy distillation persist at high loss, account for up to 18% of outputs, absorb large gradient norms, but add negligible value to reasoning performance.
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
citing papers explorer
-
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
DDE models class-wise positive feature Gaussians and negative label distributions to boost ID accuracy and OOD detection in zero-shot noisy TTA, reporting 3.70% harmonic mean gain and 6.20% FPR95 drop on ImageNet.
-
Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
TOPD improves on-policy distillation for LLM reasoning by using near-future guidance to identify divergent states, raising average accuracy from 47.8% to 52.2% on math benchmarks including AIME24 and AIME25.
-
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
Rock Tokens in on-policy distillation persist at high loss, account for up to 18% of outputs, absorb large gradient norms, but add negligible value to reasoning performance.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.