Defines Conditional Distribution Matching (CDM) as finding inputs whose induced conditional distributions match a target distribution and proposes the MLGD-F inference-time algorithm using pretrained diffusion models to solve it without retraining.
Decoupled weight decay regularization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
LaTER reduces LLM token usage 16-33% on reasoning benchmarks by exploring in latent space then switching to explicit CoT verification, with gains like 70% to 73.3% on AIME 2025 in the training-free version.
MetaColloc meta-learns a universal set of neural basis functions offline so that new PDEs can be solved at test time with a single linear solve instead of per-equation neural-network optimization.
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
Reshaping outcome rewards, process signals, and rollout comparability in GRPO raises strict compile-and-semantic accuracy in agentic code repair from 0.385 to 0.535 under weak feedback.
citing papers explorer
-
Inverse Design for Conditional Distribution Matching
Defines Conditional Distribution Matching (CDM) as finding inputs whose induced conditional distributions match a target distribution and proposes the MLGD-F inference-time algorithm using pretrained diffusion models to solve it without retraining.
-
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
LaTER reduces LLM token usage 16-33% on reasoning benchmarks by exploring in latent space then switching to explicit CoT verification, with gains like 70% to 73.3% on AIME 2025 in the training-free version.
-
MetaColloc: Optimization-Free PDE Solving via Meta-Learned Basis Functions
MetaColloc meta-learns a universal set of neural basis functions offline so that new PDEs can be solved at test time with a single linear solve instead of per-equation neural-network optimization.
-
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
-
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
Reshaping outcome rewards, process signals, and rollout comparability in GRPO raises strict compile-and-semantic accuracy in agentic code repair from 0.385 to 0.535 under weak feedback.