News
AI, cybersecurity, machine learning, scraping & programming news.
214 results on this page · clear filters
Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual...
Marformer: A Transformer for Predicting Missing Data Distributions
Real decisions are made under incomplete information. If we observe only some of the random variables we need, we can predict the others. The conditional marginals over the missing variables are the key ingredient for computing Ba...
Decoupling Exploration from Optimization in RLVR
Reinforcement learning with verifiable rewards has become the dominant recipe for improving the reasoning abilities of language models. RLVR samples solutions to problems, scores each solution with a programmatic verifier, and shi...
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting,...
Why Forget-Only Unlearning Needs Memorization
Reinforcement learning with verifiable rewards has become the dominant recipe for improving the reasoning abilities of language models. RLVR samples solutions to problems, scores each solution with a programmatic verifier, and shi...
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt. Several new datasets and studies have examined...
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adap...
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
The problem of evaluating large language models becomes acute when the questions asked have no single correct answer. Policy worth, option selection, competing values—these are the everyday questions put to LLMs that resist tradit...
Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective
Conformal prediction has become a standard tool for uncertainty quantification because it produces prediction sets with finite-sample coverage guarantees under minimal assumptions. Practitioners routinely treat the size of these s...
IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation remains chal...