Home Knowledge Base Stability of Score

Stability of Score

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

On Forgetting and Stability of Score-based Generative models

arXiv:2601.21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provides quantitative bounds on the sampling error of score-based generative models by leveraging stability and forgetting properties of the Markov chain associated with the reverse-time dynamics. Under weak assumptions, we provide the two structural properties to ensure the propagation of...

arXiv CS 6d ago

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning

Announce Type: replace Abstract: Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same model, strategy, and task can produce meaningfully different answers and costs across repeated executions, even under greedy decoding (T = 0). This variance is not a statistical nuisance: the highest-performing strategy wins only 77% of head-to-head runs against its nearest competitor, meaning a single observed score can silently misrank systems. We introduce ReasonBench,...

arXiv CS 8d ago

RobustModelMaker: Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning

arXiv:2606.01566v1 Announce Type: new Abstract: Small-to-medium scientific datasets place machine learning pipelines under two compounding pressures. Single-run feature selection produces feature sets that change substantially under small perturbations of the training data, and any procedure that uses the same data for selection, tuning, and evaluation produces optimistically biased performance estimates. The two failure modes are routinely treated as separable, but in the regimes where...

arXiv CS 8d ago

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

arXiv:2606.06943v1 Announce Type: new Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations. Recent test-time adaptation defenses improve robustness by leveraging many augmented views, but this leads to impractical slowdown and a clear robustness-throughput trade-off. To address this challenge, we present Stability and Suitability-guided Test-time Prompt Tuning (SS-TPT), evaluating the quality of...

arXiv CS 2d ago

Finding Most Influential Sets

arXiv:2606.05919v2 Announce Type: replace-cross Abstract: Identifying most influential sets (MIS) - size-$k$ subsets whose removal maximally changes a target estimand - is typically infeasible because it requires searching over $\binom{n}{k}$ subsets. For estimands with linear-fractional leave-set-out effects, we show that MIS selection reduces to a one-parameter sequence of top-$k$ problems. Dinkelbach's method yields an algorithm with $\mathcal{O}(n)$ cost per iteration and finite termination.

arXiv CS 2d ago

Finding Most Influential Sets

arXiv:2606.05919v1 Announce Type: cross Abstract: Identifying most influential sets (MIS) - size-$k$ subsets whose removal maximally changes a target estimand - is typically infeasible because it requires searching over $\binom{n}{k}$ subsets. For estimands with linear-fractional leave-set-out effects, we show that MIS selection reduces to a one-parameter sequence of top-$k$ problems. Dinkelbach's method yields an algorithm with $\mathcal{O}(n)$ cost per iteration and finite termination.

arXiv CS 5d ago

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding

arXiv:2602.06161v2 Announce Type: replace Abstract: Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we observe that existing verification schemes frequently trigger flip-flop oscillations, where tokens are remasked and later restored unchanged. This behaviour slows inference in two ways: remasking verified...

arXiv CS 9d ago

Ask HN: What are tools you have made for yourself since the advent of AI?

I've made a number of ceramic molds for slumping fused glass into bowls. As well as wooden templates for ceramic mugs. I've devised a few carrying tools to move glass frit paintings from my studio down to my barn where the kilns sit without spilling the glass.

Hacker News 2d ago

Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints

Announce Type: new Abstract: Task planning often suffers from severe efficiency bottlenecks when robots must reason over long-horizon action sequences under complex logical constraints, including object affordances, spatial relationships, and sequential action dependencies. Recent neuro-symbolic methods improve planning efficiency by learning object-importance scores to prune task-irrelevant objects, but they typically rely on fixed offline supervision generated from full search spaces. This...

arXiv CS 2d ago

Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization

arXiv:2606.09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm. By using a stronger teacher model to provide dense, fine-grained supervision for sampled trajectories, OPD offers a clear advantage over reinforcement learning with verifiable rewards (RLVR), which typically depends on sparse binary or outcome-based environmental feedback. However, naive token-level distillation can suffer from gradient instability, due to...

arXiv CS 1d ago