Category
3,533 papers
Fixed Model.jacobian (used by information, design and fit) took its finite-difference step as 1e-6 * max(|theta|, 1e-3). For a parameter smaller than 1e-3 in its own units the step, 1e-9, was too coarse; for a time constant of 1e-9 s it was the size of the parameter itself. The planned error bars then depended on the u...
Let b(n) be a strictly increasing sequence of positive integers satisfyinglim_{n→∞} b(n+1)/b(n) = 1. Define a recurrence by taking a_n to be the element of b nearest to a_{n-1} + a_{n-2}, with ties broken by taking the smaller element. We prove that for any initial values a_1, a_2 in b, lim_{n→∞} a_n / a_{n-1} = φ := (...
Companion to the paper Immaterial Apart, Material Together: Statement-Level Disclosure Regulation under Cheap Machine Aggregation by Lisha Ai and Xiaoyu Chen. Chinese listed firms answer thousands of small investor questions on the exchanges' interaction platforms; each answer passes review on its own. A language model...
ClusterFewshot is proposed, a strategy that combines semantic structuring with utility-aware scoring to construct representative and effective few-shot demonstration sets and substantially reduces optimization cost across multiple benchmarks.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work identifies a systematic upstream/downstream structure in dLLM rollouts and proposes Informed Masking (IM), which derives a per-token priority score from the denoising trajectory at zero extra inference cost and biases mask sampling toward downstream tokens.
We study what LLMs do when a user applies pressure in an uncomfortable situation: a user insists, begs, flatters or grieves, and the model gives up a correct fact, writes a document it should refuse, or cheers a plan that will cost the user money. We send frozen multi-turn scenes, identical for every model regardless o...
Face/Off is introduced, a semantics-preserving identifier-renaming framework, and progressive naming conditions across multiple models and code-comprehension tasks are evaluated, revealing a systematic vulnerability in how current LLMs balance lexical cues against program structure.
EquivSVA, a formally verified dataset organized around behavior families, illustrates how behavior-family organization can support controlled stud- ies of assertion-generation robustness without requiring changes in intended functionality.
MT-ProtBERT consistently outperforms PARROT, an RNN-based IDP-specific model, across all tasks, and demonstrates that combining self-supervised and biochemistry-informed tasks, and multi-scale learning enables robust modeling of unstructured proteins under data scarcity.
A small concept generator is optimized with reinforcement learning so that its concepts maximize the downstream success of a larger, frozen answer generator, and can thus be trained into an effective, reusable search policy for a much larger one.
NSFT (Neural Sub-expert Fine-Tuning), a fine-grained PEFT framework that refines MoE adaptation from experts to sub-experts, is proposed and suggests that sub-expert-level adaptation is a more precise and efficient PEFT paradigm for MoE LLMs.
Results show that persistent program growth can move recurring control out of model context and into low-cost code, yielding reusable specialist agents that remain effective with smaller deployment models.
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
