Akademik Araştırma
& Analytics.
ArXiv veritabanından canlı olarak çekilen, yapay zeka ve makine öğrenimi alanındaki en son akademik yayınları keşfedin.
Symmetry in language statistics shapes the geometry of model representations
Although learned representations underlie neural networks' success, their fundamental properties remain poorly understood. A striking example is the emergence of simple geometric structures in LLM representations: for example, calendar months organiz...
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
Large language models (LLMs) are increasingly deployed in privacy-critical and personalization-oriented scenarios, yet the role of context length in shaping privacy leakage and personalization effectiveness remains largely unexplored. We introduce a ...
Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation
Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equivariance through architectural constraints such as equivariant denoiser...
Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI
Cross-survey generalization is a critical challenge in stellar spectral analysis, particularly in cases such as transferring from low- to moderate-resolution surveys. We investigate this problem using pre-trained models, focusing on simple neural net...
Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation
Bio-pharmaceutical innovation has shifted: many new drug assets now originate outside the United States and are disclosed primarily via regional, non-English channels. Recent data suggests >85% of patent filings originate outside the U.S., with China...
Scaling Beyond Masked Diffusion Language Models
Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on language mo...
Cold-Start Personalization via Training-Free Priors from Structured World Models
Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available. The core challenge is a routing problem: each task admits dozens of preference dimensions, yet individual users car...
BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames
Many robot tasks require attending to the history of past observations. For example, finding an item in a room requires remembering which places have already been searched. However, the best-performing robot policies typically condition only on the c...
Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling efficiency of score-based discrete diffusion models under a continuous-tim...
ArXiv API Entegrasyonu
Bu sayfa doğrudan arXiv.org veritabanından veri çekmektedir. Listelenen tüm içerikler global akademik topluluk tarafından paylaşılan open-access yayınlardır.