Model collapse occurs in structured interactive learning if and only if the directed interaction graph satisfies a specific topological condition, with finite-sample guarantees for linear regression and asymptotic results for M-estimators.
hub
Advances in neural information processing systems , volume=
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
A novel decoupled method for distributed saddle problems achieves optimal communication complexity via multi-stage residual norm minimization, with a matching lower bound and extension to variational inequalities.
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
A two-stage symbolic regression plus generative model framework recovers governing interaction terms and forcing in stochastic triad models while accurately predicting statistical moments up to order five.
RetinaDiff uses phase correlation to create a motion-corrected physics prior and then applies a conditional diffusion model to reconstruct high-quality temporal LSCI from extremely limited frames.
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
Sparse local 2D articulated cues extracted from monocular non-human character videos can condition a human motion generator to produce high-fidelity, editable human reenactments that preserve essential dynamics.
A CNN trained on AREPO simulations and synthetic observations reverts edge-on 13CO spectral data to top-down views of the CMZ as a proof-of-concept for supervised reversion.
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
A delighting network trained via Dataset Latent Modulation on heterogeneous OLAT and Light Stage data enables high-quality in-the-wild facial reflectance capture from video and produces the NeRSemble-Scan dataset.
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.
Adversarial optimal transport objectives jointly learn summary statistics and a chaotic-system emulator from a single noisy trajectory, improving long-term statistical fidelity over handcrafted-feature baselines.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
ActDiff-VC partitions video into segments, transmits adaptive keyframes and budget-aware point trajectories, and reconstructs frames via conditional diffusion, reporting up to 64.6% bitrate reduction at matched NIQE on UVG and MCL-JCV.
A structured diffusion bridge method achieves near fully-paired modality translation quality using alignment constraints even in unpaired or semi-paired regimes.
Discriminator-informed resampling via normalizing flows reduces error in the EnGMF for low-ensemble regimes on the Ikeda map and Lorenz '63 system.
citing papers explorer
-
When Does Model Collapse Occur in Structured Interactive Learning?
Model collapse occurs in structured interactive learning if and only if the directed interaction graph satisfies a specific topological condition, with finite-sample guarantees for linear regression and asymptotic results for M-estimators.
-
Efficient Gradient Methods for Distributed Saddle Problems
A novel decoupled method for distributed saddle problems achieves optimal communication complexity via multi-stage residual norm minimization, with a matching lower bound and extension to variational inequalities.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
The finite expression method for turbulent dynamics with high-order moment recovery
A two-stage symbolic regression plus generative model framework recovers governing interaction terms and forcing in stochastic triad models while accurately predicting statistical moments up to order five.
-
Physics-Informed Conditional Diffusion for Motion-Robust Retinal Temporal Laser Speckle Contrast Imaging
RetinaDiff uses phase correlation to create a motion-corrected physics prior and then applies a conditional diffusion model to reconstruct high-quality temporal LSCI from extremely limited frames.
-
Detecting Pretraining Data from Large Language Models
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
-
AnyAct: Towards Human Reenactment of Character Motion From Video
Sparse local 2D articulated cues extracted from monocular non-human character videos can condition a human motion generator to produce high-fidelity, editable human reenactments that preserve essential dynamics.
-
IRIS: Deciphering Spectral-Line Imagery of the Galactic Center by Machine-Learning on Simulations
A CNN trained on AREPO simulations and synthetic observations reverts edge-on 13CO spectral data to top-down views of the CMZ as a proof-of-concept for supervised reversion.
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
-
DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
-
Learning a Delighting Prior for Facial Appearance Capture in the Wild
A delighting network trained via Dataset Latent Modulation on heterogeneous OLAT and Light Stage data enables high-quality in-the-wild facial reflectance capture from video and produces the NeRSemble-Scan dataset.
-
Concentration and Calibration in Predictive Bayesian Inference
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.
-
Learning to Emulate Chaos: Adversarial Optimal Transport Regularization
Adversarial optimal transport objectives jointly learn summary statistics and a chaotic-system emulator from a single noisy trajectory, improving long-term statistical fidelity over handcrafted-feature baselines.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
-
Lossless Anti-Distillation Sampling
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
ActDiff-VC partitions video into segments, transmits adaptive keyframes and budget-aware point trajectories, and reconstructs frames via conditional diffusion, reporting up to 64.6% bitrate reduction at matched NIQE on UVG and MCL-JCV.
-
Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
A structured diffusion bridge method achieves near fully-paired modality translation quality using alignment constraints even in unpaired or semi-paired regimes.
-
Learning Discriminators for Resampling in the Ensemble Gaussian Mixture Filter through a Normalizing Flow Approach
Discriminator-informed resampling via normalizing flows reduces error in the EnGMF for low-ensemble regimes on the Ikeda map and Lorenz '63 system.