Generalization through Lexical Abstraction in Transformer Models: The Case of Functional Words
Research
Research News
New papers, breakthroughs and academic AI research
MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution
Research
SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings
Research
JustMem: Just-Enough Memory Access for Long-Term Conversations
Research
D-Quant: Driftable Entropy Coding for KV Cache Quantization
Research
Evaluating Communicative Success in Machine-Translated Conversation
Research
Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference
Research
FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity
Research
V\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering
Research
PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces
Research
KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms
Research
Intrinsic Sequence-Likelihood Confidence in Retrieval-Dominated Extractive QA: Two Pre-Specified Negatives, and What They Do and Do Not Attribute
Research