# GFlowNets

3 related articles

Subscribe to updates

arXiv Nov 3, 2026
Discounting rewards by density: DARS stops GRPO collapsing onto one high-reward mode, cutting mode-mass error to 0.014 on a four-peak navigation task
Reinforcement learning that maximizes expected return tends to concentrate probability on a few high-reward outcomes; DARS estimates the local density of outcomes within each on-policy rollout group and inversely scales rewards by that density before standard GRPO updates. On a four-Gaussian navigation task, GRPO covers a single mode while DARS-GRPO recovers mode masses close to 0.25 each, with mode total variation 0.014 versus 0.750 for GRPO. In text-to-image prompt adaptation, DARS-GRPO raises image and prompt diversity across datasets, policy language models and reward settings while keeping semantic alignment.
Reinforcement learning that maximizes expected return tends to concentrate probability on a few high-reward outcomes; DARS estimates the local density of outcomes within each on-policy rollout group and inversely scales rewards by that density before standard GRPO updates. On a four-Gaussian navigation task, GRPO covers a single mode while DARS-GRPO recovers mode masses close to 0.25 each, with mode total variation 0.014 versus 0.750 for GRPO. In text-to-image prompt adaptation, DARS-GRPO raises image and prompt diversity across datasets, policy language models and reward settings while keeping semantic alignment.
National University of Singapore
Ria Shekhawat（First author）
Density-Aware Reward Scaling GRPO Reward-Proportional Sampling Text-to-Image Prompt Adaptation GFlowNets
arXiv Oct 30, 2026
GFlowNets learn their own generation order: four of five runs converge on checksum tasks where a uniform backward policy never does
GFlowNets build discrete objects one component at a time, and the order determines which conditional distributions the network must learn. Previously the order was fixed by a preset or uniform backward policy, and standard training struggled to find useful orders. Learning-Order GFlowNet learns positions and symbols jointly without order labels, converging in four of five runs on checksum dependencies, against zero for a uniform backward policy and two of ten for fixed random orders.
GFlowNets build discrete objects one component at a time, and the order determines which conditional distributions the network must learn. Previously the order was fixed by a preset or uniform backward policy, and standard training struggled to find useful orders. Learning-Order GFlowNet learns positions and symbols jointly without order labels, converging in four of five runs on checksum dependencies, against zero for a uniform backward policy and two of ten for fixed random orders.
Timofei Gritsaev（First author）
GFlowNets Learning-Order GFlowNet Generation order learning Trajectory Balance Gradient signal-to-noise ratio analysis
arXiv Sep 30, 2026
Tsinghua team turns the SIS proposal into a learning problem with GFlowNets: one network zero-shot matches or beats the post-hoc best of 31 analytic proposals on 1,190 unseen margins
The work shows that the zero-variance sequential importance sampling (SIS) proposal for binary matrices with fixed margins is exactly the policy of a unit-reward GFlowNet, and proposes MarginFlow, a set transformer that reads the remaining margins and, trained on 1,904 margins, runs zero-shot on 1,190 held-out margins, matching or beating the post-hoc best of 31 analytically designed configurations on 1,187 of them with a median effective sample fraction of 99.8%.
The work shows that the zero-variance sequential importance sampling (SIS) proposal for binary matrices with fixed margins is exactly the policy of a unit-reward GFlowNet, and proposes MarginFlow, a set transformer that reads the remaining margins and, trained on 1,904 margins, runs zero-shot on 1,190 held-out margins, matching or beating the post-hoc best of 31 analytically designed configurations on 1,187 of them with a median effective sample fraction of 99.8%.
Tsinghua University
Ruishuo Chen（First author）
MarginFlow GFlowNets Sequential Importance Sampling Binary Matrices with Fixed Margins

You’re all caught up

Discounting rewards by density: DARS stops GRPO collapsing onto one high-reward mode, cutting mode-mass error to 0.014 on a four-peak navigation task

GFlowNets learn their own generation order: four of five runs converge on checksum tasks where a uniform backward policy never does

Tsinghua team turns the SIS proposal into a learning problem with GFlowNets: one network zero-shot matches or beats the post-hoc best of 31 analytic proposals on 1,190 unseen margins