ArXiv Live Feed

Research
& Analytics.

Explore the latest academic publications in AI and machine learning, pulled live from the ArXiv database.

PAPER / 6/18/2026

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...

Joshua Engels, Callum McDougall, Bilal Chughtai, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue, João Gabriel Lopes de Oliveira, Rohin Shah, Neel Nanda
Read Full Paper
PAPER / 6/18/2026

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...

Wenhao Chi, Arkaprava Sinha, Dominick Reilly, Hieu Le, Srijan Das
Read Full Paper
PAPER / 6/18/2026

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...

Georgy Noarov, Aaron Roth
Read Full Paper
PAPER / 6/18/2026

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...

Ruizhong Qiu, Yinglong Xia, Dongqi Fu, Hanqing Zeng, Ren Chen, Xiangjun Fan, Hong Li, Hong Yan, Hanghang Tong
Read Full Paper
PAPER / 6/18/2026

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...

Przemyslaw Musialski
Read Full Paper
PAPER / 6/18/2026

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...

Linda Lu, Karthik Sridharan
Read Full Paper
PAPER / 6/18/2026

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...

Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa, Anqi Liu
Read Full Paper
PAPER / 6/18/2026

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 ...

Qingyang Zhu, Eric Karl Oermann, Kyunghyun Cho
Read Full Paper
PAPER / 6/18/2026

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.

arXiv.org'u Keşfet