Anthropic watermark rollout leaves loophole on two older Claude models
API users can bypass watermark on Claude Opus 4.6 and Sonnet 4.6 by changing sampling parameters.
Stories per day · 30 days
3 RSS
Relatedgenerative-models23d-assets1ai-act1anthropic1claude1consistency-distillation1diffusion-models1discrete-diffusion1diversity1inverse-problems1loophole1msr1ode1test-time1text-to-image1watermark1
19 stories, newest first · one card per story
Stories tagged #sampling
Exponential residual flows give an ODE sampler for discrete diffusion
The construction preserves the original diffusion's marginals and is specialized to masked and uniform diffusion.
Prior-Consistent DAPS Improves Diffusion Sampling for Nonlinear Inverse Problems
PC-DAPS prunes candidates by prior consistency without ground truth to reduce prior-inconsistent samples on ambiguous nonlinear problems.
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
MSR improves generative-model diversity by sampling corpus-derived attributes and using the model only as a renderer.
KL Before and After Mixing: A Round-Complexity Separation in Parallel Sampling
Theory paper separates two KL measures for parallel sampling, with very different round costs.
AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis
Researchers release AMLworld-Compact, cutting AML LLM evaluation targets by up to 611x with weighted precision and F1 estimates.
Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
Corrected two-level softmax samplers remove cluster-size and dispersion bias with little overhead.
Direct Intermediate Initialization for Tilted Diffusion Samplers
Direct intermediate initialization improves tilted diffusion SMC samplers on Gaussian-mixture inverse problems.
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
An agentic RAG budget study finds broader question coverage reduces evaluation error more than extra reads or trajectories.
Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
A momentum-preconditioned Langevin sampler stays stable for nonconvex, non-Lipschitz matrix potentials.
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Parallel Power Tempering improves inference-time reasoning, matching frontier models without RL post-training.
Tail-Influence Sampling for CVaR Policy Evaluation
Tail-Influence Sampling reallocates evaluation queries to cut CVaR estimation error, reducing CliffWalking MSE by up to 76%.
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Parallel Power Tempering improves inference-time power sampling so small models match frontier reasoning without RL updates.
Tail-Influence Sampling for CVaR Policy Evaluation
Tail-Influence Sampling reallocates evaluation queries to estimate policy CVaR more accurately under a fixed budget.
First-Order Stationarity of Reverse Diffusions
SDE reverse flows of Langevin diffusions contract Fisher divergence when the noising potential is strongly convex.
A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model
Researchers prove nearly quadratic lower bounds for linear optimization over convex bodies in the membership oracle model.
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
FLEET matches repeated sampling accuracy at 3x speed and raises LiveCodeBench Pass@32 from 59.9% to 66.2%.
Schedule optimization for tau-leaping in masked discrete diffusion
A theory paper derives optimal denoising schedules for tau-leaping samplers in masked discrete diffusion models.
Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start
Thin-shell stability proof along the Gaussian cooling path improves cold-start logconcave sampling complexity to near n^2.5 from n^2.75.