Research
& Analytics.
Explore the latest academic publications in AI and machine learning, pulled live from the ArXiv database.
How Transparent is DiffusionGemma?
LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, DiffusionGemma performs a larger fraction of its computation in a continuous...
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning
Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action. We argue that a truly expressive egocentric re...
Optimal Deterministic Multicalibration and Omniprediction
A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweighting contexts by each $g \in G$. It is a useful property for many downs...
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical behaviors. At the core of generative recommendation lies item tokenization...
The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups
We place the attention token on the group: a token is an element $g_i$ of a matrix Lie group $G$ -- a bare transformation, with no feature payload and no external action $ρ(g)$ carrying it. To our knowledge this is the first attention construction wh...
Predictability as a Fine-Grained Measure for Privacy
Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-accuracy tradeoff. We introduce privacy via predictability, a fine-gra...
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent work shows that enforcing calibration at the level of individual predict...
Multi-Task Bayesian In-Context Learning
Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization. However, exact inference is often intractable, and scalable approximations may remain computationally expensive ...
Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving
Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache...
ArXiv API Entegrasyonu
This page pulls data directly from the arXiv.org database. All listed contents are open-access publications shared by the global academic community.