Featured Papers
Popular high-signal papers with direct links to full protocol pages.
- POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- DEBISS: a Corpus of Individual, Semi-structured and Spoken Debates
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Ensembling Language Models with Sequential Monte Carlo
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- Dissociating Direct Access from Inference in AI Introspection
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.
- An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
Mar 5, 2026 · Citations: 0
Open the paper page for extracted protocol signals, benchmark mentions, and evaluation context.