Computer Science
While Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning tasks through collaborative interaction, optimizing their dynamics remains a formidable challenge due to the discrete, non-differentiable nature of…
Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation. However, dexterous manipulation remains challenging for VLA policies due to…
Clustering is an unsupervised technique for grouping data points by similarity. While explainability methods exist for supervised machine learning, they are not directly applicable to clustering, making it challenging to understand cluster…
We introduce TriSearch, a reinforcement learning framework for optimizing objectives over triangulations of a polytope via bistellar flips. The key idea is a circuit-supported subtriangulation action representation: feasible flips are…
Long-horizon interactions require language models to manage accumulating information: when to update their state, when to preserve their state, and what to ignore. We study this challenge as \textbf{Contextual Belief Management (CBM)}:…
Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larger batch. Existing fixes use batch-invariant operators or LLM-42's per-token…
Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in computer vision. Yet emerging evidence suggests that contiguous transformer layers…
Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with…
Continuous-time models are a natural choice for irregular and asynchronous data. A central design choice is how to embed discrete observations into continuous time. Interpolation- and imputation-based embeddings reconstruct a continuous…
Electronic identities (eIDs) are crucial in an increasingly digitalized environment. Pseudonyms, as offered by Austria's governmental sector-specific personal identifiers (bPks), can significantly improve privacy by ensuring that personal…
Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Object Tracking (MOT) focuses on associating pre-defined object detections or segmentations.…
AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that…
The same prompt -- "best CRM software" -- reaches AI assistants from buyers in widely different contexts: a solo founder, an enterprise VP, a UK SMB owner. We audit how strongly that contextual variation reshapes which brands the model…
Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, existing open-domain retrieval methods rely heavily on surface-level lexical…
The membership inference problem for publicly released statistics from a private dataset is well-studied. When developing and formally analyzing attack strategies, however, the focus has been on attacks that model the population using only…
Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We…
We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while…
The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and students, especially for K-12 education. By developing a triadic collaboration system to…
Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can…
Diffusion-based planning has achieved strong results in single-agent offline reinforcement learning, yet scaling to many-agent systems remains intractable due to the curse of dimensionality in the joint trajectory space. We introduce…