🧠 LLMs - sbhargava92 · Scour

How to build custom reasoning agents with a fraction of the compute 🤖AI Agents

venturebeat.com·2d

Android Bench - Evaluating LLMs On The Android Platform ⚙️Systems Programming

i-programmer.info·1d

Language Generation in the Limit 🤖AI Agents

openreview.net·6d

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models 🗄️Vector Databases

RNN to Transformer NMT: PyTorch Migration with 2.8x BLEU Gain 🗄️Vector Databases

tildalice.io·6d

From $200 to $30: Five Layers of LLM Cost Optimization 💾Storage Engines

blog.dwornikowski.com·6d·Hacker News

Granite 4.1 LLMs: How They’re Built 🤖AI Agents

huggingface.co·1d·Hacker News

Adaptive Thinking: Large Language Models Know When to Think in Latent Space 🤖AI Agents

machinelearning.apple.com·2d

Statistical Structure and the Failure of Pointing: A System-Class Law for Compression-Based Generative Systems 🗄️Vector Databases

philsci-archive.pitt.edu·4d

AutoSP: Long-Context LLM Training via Compiler-Based Sequence Parallelism ⚙️Systems Programming

pytorch.org·1d·Hacker News

Training a Transformer to Compose One Step Per Layer (and Proving It) 🗄️Vector Databases

lesswrong.com·4d

Spurious alignment between large language models and brains can emerge from non-robust methods and overlooked confounds 🗄️Vector Databases

This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms. 🤖AI Agents

Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning 🤖AI Agents

umbecanessa/neural-ledger-system: An inference architecture that makes LLMs stateful. Patent pending (US 64/050,345). 🤖AI Agents

github.com·2d·Hacker News

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients 🤖AI Agents

LLM-Flax : Generalizable Robotic Task Planning via Neuro-Symbolic Approaches with Large Language Models 🤖AI Agents

AsishKumarDalal/memoryllm: using differntiable neural computer architecture with GPT2 to provide memory ⚙️Systems Programming

github.com·5d·DEV

Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens ⚙️Systems Programming

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control 🤖AI Agents

Log in to enable infinite scrolling