Tag
This paper proposes a gloss-free representation learning approach for cross-dataset sign spotting, using weakly aligned broadcast transcripts in Turkish Sign Language. It shows that LLM-assisted pseudo-gloss normalization improves temporal localization and downstream translation quality.
This paper proposes CONFER, a graph-based conflict-aware evidence negotiation framework for weakly supervised multimodal emotion recognition, addressing self-report unreliability and cross-modal conflict. It achieves competitive accuracy on AMIGOS, MAHNOB-HCI, and DEAP benchmarks.
This paper proposes a preference-based learning framework for antibody expression ranking, integrating scarce quantitative data with large-scale weak positive supervision from immunization sequences. The method adapts Direct Preference Optimization to protein language models using a union-masked log-likelihood approximation and IMGT-based alignment, achieving improved ranking performance on a diverse internal dataset.
This paper proposes a graph-based framework that combines weak supervision with propagation graph analysis to detect and analyze disinformation narratives in Telegram ecosystems, focusing on Russian and Ukrainian channels.
This paper presents two machine learning frameworks for detecting LDAP reconnaissance attacks: an ML classifier using weak supervision to predict malicious queries and a statistical hypothesis-testing method for mining novel malicious signatures, achieving practical detection performance.
This paper investigates the behavioral drivers of incongruence between star ratings and textual sentiment in Sri Lankan tourism reviews, finding that 18.6% of reviews show mismatch with six directional patterns, and identifying venue type, reviewer expertise, and temporal factors as contributors.
This paper introduces Preference Delta Aggregation (PDA) and Geometric Alignment Merging (GAM) to aggregate multiple 'weak' preference signals from weaker model pairs via LoRA merging, improving strong LLMs on knowledge reasoning and agentic search tasks by over 6% on average.
This paper introduces LogMILP, a weakly-supervised framework for log instance anomaly localization that uses prototype-guided structural modeling and counterfactual perturbation consistency regularization to improve detection and interpretability with only bag-level labels.
This paper introduces a two-stage neuro-symbolic framework that uses weak supervision (as little as 1% labels) with a slot-based VAE to learn interpretable symbols for object-centric visual reasoning, outperforming foundation models in domain generalization.
This paper systematically studies when LLMs can generalize in reasoning tasks under weak supervision (scarce data, noisy rewards, self-supervised proxy rewards), finding that reward saturation dynamics and reasoning faithfulness are key predictors, and that SFT on explicit reasoning traces is necessary for successful generalization under weak supervision.
OpenAI's Superalignment team introduces weak-to-strong generalization, a new research direction for empirically aligning superhuman AI models by addressing the fundamental challenge of how weak human supervisors can reliably control and steer AI systems vastly smarter than themselves.
The article explains 'Vokenization,' a multimodal learning technique that bridges computer vision and natural language processing by using weak supervision to link visual data with language tokens. It contrasts this approach with text-only models like GPT-3 and BERT, highlighting how visual grounding can improve language understanding.