STARE uses step-wise RL to attack multimodal models, achieving 68% higher attack success rate while revealing that adversarial optimization concentrates conceptual toxicity early and detail toxicity late in the generation trajectory.
The power of scale for parameter-efficient prompt tuning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
CAAT selects critical parameters for adversarial robustness in ViTs and applies PEFT to tune only those, yielding a 4.3% robustness drop versus full AT while using ~6% of parameters.
FactNet is a billion-scale multilingual knowledge graph that links 1.7B Wikidata assertions to 3.01B byte-precise evidence spans from 316 Wikipedia editions, accompanied by a leakage-controlled benchmark suite.
RE-TAB uses a deterministic LCS-based table-state reward for stepwise guidance and test-time scaling, raising LLM table-reasoning accuracy by 26.7 pp on average across six backbones and three benchmarks.
LLMs share task-specific attention heads across prompting styles, with activation strength explaining performance differences and failures arising from competing representations.
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
citing papers explorer
-
STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
STARE uses step-wise RL to attack multimodal models, achieving 68% higher attack success rate while revealing that adversarial optimization concentrates conceptual toxicity early and detail toxicity late in the generation trajectory.
-
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
CAAT selects critical parameters for adversarial robustness in ViTs and applies PEFT to tune only those, yielding a 4.3% robustness drop versus full AT while using ~6% of parameters.
-
FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
FactNet is a billion-scale multilingual knowledge graph that links 1.7B Wikidata assertions to 3.01B byte-precise evidence spans from 316 Wikipedia editions, accompanied by a leakage-controlled benchmark suite.
-
Enhancing Table Reasoning with Deterministic Table-State Rewards
RE-TAB uses a deterministic LCS-based table-state reward for stepwise guidance and test-time scaling, raising LLM table-reasoning accuracy by 26.7 pp on average across six backbones and three benchmarks.
-
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
LLMs share task-specific attention heads across prompting styles, with activation strength explaining performance differences and failures arising from competing representations.
-
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.