This paper predicts the aggregate crowd salience of a document from its text before its marks accumulate.

This paper investigates whether a group of people highlighting the same document forms a single consensus or is internally structured into reader sub-groups.

This paper investigates how individual agent biases amplify system-wide unfairness in multi-agent systems, demonstrating that uniform exposure to bias can elevate overall bias beyond the sum of indivi…

This study demonstrates that instruction-tuned language model agents exhibit robust, group-contingent in-group bias, structurally mimicking human social biases, even when standard action logs fail to…

The paper proposes a privacy-preserving system for crowd monitoring that counts individuals across different locations and time periods using face recognition without ever revealing personal identitie…

The study demonstrates that conditioning AI brand recommendations on a user's persona significantly alters the recommended product set, particularly for mid-market brands, and this effect is largest o…

Equilibrated Diffusion introduces a frequency-aware approach to image customization, disentangling style and subject content embeddings to achieve superior subject fidelity and text adherence.

The paper introduces CASTER, a new human-centric task for evaluating User-Generated Content (UGC) resonance, and proposes MEDEA, an architecture that uses a Social Chain-of-Thought mechanism to simula…

The paper proposes WEINCE, a modified InfoNCE objective that uses extreme value theory corrections to improve contrastive learning by more accurately modeling the selection of hard negative examples.

The study found that while contextualizing AI responses reduces their persuasive power, combining this technique with conversational warmth restores persuasiveness, suggesting that user deference to A…

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

The study finds that specific, interpretable neuron populations (Rosetta Neurons) exhibit predictable, scale-dependent changes in selectivity and specialization as neural models grow larger.

The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

The paper introduces Context-Dependent Argumentation Frameworks (CDAFs) to model how an agent strategically manipulates the success of arguments by choosing the external evaluation context.

This paper proposes a unified evaluation framework for hate speech detection that systematically assesses model performance and explainability across various label and rationale representation spaces,…

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…

The paper evaluates LLM-generated reactions to Spanish online news, finding that off-the-shelf models fail to accurately reproduce the measurable properties of real audience discourse, and even fine-t…

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

The paper proposes moving the query instead of the KV-cache during cross-instance attention, demonstrating that this approach is significantly cheaper than moving the cache, especially on modern GPU f…