robustness

Tag

Cards List
#robustness

Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness

arXiv cs.LG ↗ · 2026-05-25 Cached

This paper presents the first implementation of an infra-Bayesian reinforcement learning agent, demonstrating that it outperforms classical RL in worst-case regret and handles Newcomb's problem optimally, offering a step toward robustness under model misspecification.

0 favorites 0 likes
#robustness

Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

arXiv cs.AI ↗ · 2026-05-25 Cached

This paper introduces ASAM (Adversarial Subspace Alignment for Multimodal Knowledge Editing), a method that improves the generality of intrinsic multimodal knowledge editing by generating adversarial yet semantically coherent variants and enforcing low-rank alignment of representations, addressing the limited generalization of existing methods.

0 favorites 0 likes
#robustness

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Hugging Face Daily Papers ↗ · 2026-05-25 Cached

Introduces GARD, a diffusion-based framework that operates in the feature space of a feed-forward 3D reconstructor to jointly recover scene geometry and high-quality imagery from degraded inputs.

0 favorites 0 likes
#robustness

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

arXiv cs.CL ↗ · 2026-05-21 Cached

This paper investigates the conflict between instruction-following and pattern completion in LLMs, finding that instruction-following is brittle under induction pressure and varies widely across models, with output diversity being the primary factor for robustness.

0 favorites 0 likes
#robustness

Robust Subspace-Constrained Quadratic Models for Low-Dimensional Structure Learning

arXiv cs.LG ↗ · 2026-05-21 Cached

This paper proposes a robust subspace-constrained quadratic model for learning low-dimensional structures from high-dimensional data, accommodating heavy-tailed noise. A gradient-based algorithm with backtracking line search is developed, and experiments show improved robustness and reconstruction accuracy.

0 favorites 0 likes
#robustness

SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation

Hugging Face Daily Papers ↗ · 2026-05-21 Cached

SpaceDG is a large-scale dataset and benchmark that evaluates multimodal language models' spatial reasoning robustness under visual degradations like motion blur and low light, revealing significant performance gaps and showing that fine-tuning on SpaceDG improves robustness without degrading clean image performance.

0 favorites 0 likes
#robustness

Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods

arXiv cs.LG ↗ · 2026-05-20

A survey on quantum adversarial machine learning, covering attacks, defenses, and theoretical underpinnings.

0 favorites 0 likes
#robustness

When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach

arXiv cs.AI ↗ · 2026-05-20

This paper studies whether tabular foundation models based on pretrained prior-data fitted networks (PFNs) can generalize to strategic tabular data where individuals modify features after deployment. It proposes Strategic Prior-data Fitted Network (SPN), an inference-time framework that aligns PFN predictions with the post-manipulation distribution without retraining.

0 favorites 0 likes
#robustness

How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence

arXiv cs.CL ↗ · 2026-05-20 Cached

This paper identifies Footprint Bias in document layout analysis robustness evaluation and proposes a structure-aware auditing framework that decouples probe construction and pathway attribution, showing that small structurally targeted probes cause comparable downstream degradation to larger perturbations.

0 favorites 0 likes
#robustness

Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints

Hugging Face Daily Papers ↗ · 2026-05-20 Cached

This paper introduces SLIM, a minimal architecture that decouples communication from policy representation in multi-agent reinforcement learning, achieving state-of-the-art performance under bandwidth constraints with minimal degradation.

0 favorites 0 likes
#robustness

When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning

arXiv cs.LG ↗ · 2026-05-19 Cached

This paper studies adversarial action masking in self-play reinforcement learning, where an attacker selectively removes legal actions from a victim's action set. The attack is shown to be significantly more damaging than random masking or perturbation baselines across multiple environments and algorithms, and victims do not recover under extended training.

0 favorites 0 likes
#robustness

MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion

arXiv cs.LG ↗ · 2026-05-18 Cached

MuteBench is a benchmark for evaluating multimodal fusion models under modality missing and within-modality missing conditions across clinical datasets. It provides insights into architecture robustness and suggests that diffusion-based imputation can help.

0 favorites 0 likes
#robustness

Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law

arXiv cs.AI ↗ · 2026-05-18 Cached

This paper empirically studies LLMs' legal reasoning in tax law, showing that data contamination inflates performance and that neuro-symbolic hybrid systems offer more reliable and robust generalization than monolithic LLMs.

0 favorites 0 likes
#robustness

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

Hugging Face Daily Papers ↗ · 2026-05-18 Cached

This paper introduces an Information Bottleneck Adapter (IB-Adapter) for Vision-Language-Action (VLA) models to improve robustness against unseen visual disturbances without requiring extra data, achieving up to 30% improvement with minimal parameter overhead.

0 favorites 0 likes
#robustness

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods

arXiv cs.LG ↗ · 2026-05-15 Cached

This paper investigates the resilience of AI-generated text detection methods (fine-tuned RoBERTa, Binoculars, text feature analysis, and ensembles) against paraphrasing attacks, finding that Binoculars-inclusive ensembles are most effective but also most vulnerable to attacks, highlighting a dichotomy between performance and resilience.

0 favorites 0 likes
#robustness

Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement

arXiv cs.AI ↗ · 2026-05-15 Cached

This paper proposes a novel transformer verification approach that uses ReLU to represent precise but non-linear bounds for dot products, enabling precise and efficient verification. The method outperforms state-of-the-art baselines on sentiment analysis models.

0 favorites 0 likes
#robustness

When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering

arXiv cs.CL ↗ · 2026-05-15 Cached

This paper evaluates six open-weight LLMs on biomedical QA under conflicting evidence conditions, revealing accuracy drops and prediction flips, and proposes a conflict-aware abstention score that improves selective accuracy.

0 favorites 0 likes
#robustness

Enhanced and Efficient Reasoning in Large Learning Models

arXiv cs.AI ↗ · 2026-05-15 Cached

This paper proposes a method for improving reasoning in large language models by recoding data to explicitly represent relationships, enabling efficient principled reasoning with polynomial-time learnability for relational rules, which addresses hallucinations and supports sound reasoning across multiple calls.

0 favorites 0 likes
#robustness

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

Hugging Face Daily Papers ↗ · 2026-05-15 Cached

SAE-FT introduces a novel fine-tuning method for CLIP models that uses sparse autoencoder constraints to regularize visual representations, improving robustness against distribution shifts while maintaining performance and enabling interpretability.

0 favorites 0 likes
#robustness

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

arXiv cs.LG ↗ · 2026-05-14 Cached

This paper shows that mixing post-training data into pretraining (early exposure) improves how robustly a model retains capabilities after subsequent fine-tuning, challenging the notion that immediate post-training performance predicts retention. Controlled experiments on 135M and 1B models demonstrate that early exposure consistently improves the trade-off between upstream retention and downstream performance.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback