Rag + Inference

34.0

Refine and port the cited-inference pattern to be framework-agnostic. Enable any existing LLM app to require verified citations for every generated sentence.

+34

emergingimplementation gap

reasoninguicitationhealthcareraginferenceagents

Signals (52)

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling

'Cognitive Surrender' Is a New and Useful Term for How AI Melts Brains

Improving Latent Generalization Using Test-time Compute

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs

GLM-5.1: Towards Long-Horizon Tasks

AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

Improvisational Games as a Benchmark for Social Intelligence of AI Agents: The Case of Connections

The AI Great Leap Forward

Decision-Centric Design for LLM Systems

unslothai/unsloth

ADAG: Automatically Describing Attribution Graphs

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking

TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models

RAGEN-2: Reasoning Collapse in Agentic RL

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

Hallucination as output-boundary misclassification: a composite abstention architecture for language models

HuggingFace10d ago

Training mRNA Language Models Across 25 Species for $165

Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning

Anthropic7d ago

AnnouncementsFeb 5, 2026Introducing Claude Opus 4.6We’re upgrading our smartest model. Across agentic coding, computer use, tool use, search, and finance, Opus 4.6 is an industry-leading model, often

HKUDS/AutoAgent

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Cross-Tokenizer LLM Distillation through a Byte-Level Interface

ATANT: An Evaluation Framework for AI Continuity

Google AI29d ago

Exploring the feasibility of conversational diagnostic AI in a real-world clinical study

The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse

Olmo Hybrid: From Theory to Practice and Back

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space

nvidia blog21h ago

Cut Checkpoint Costs with About 30 Lines of Python and NVIDIA nvCOMP

YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches

The tool that won't let AI say anything it can't cite

Sensitivity-Positional Co-Localization in GQA Transformers

Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets

Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling

nvidia blog23h ago

How to Accelerate Protein Structure Prediction at Proteome-Scale

SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems

Reasoning Fails Where Step Flow Breaks

NVIDIA-NeMo/DataDesigner

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma

LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

Consistency-Guided Decoding with Proof-Driven Disambiguation for Three-Way Logical Question Answering

SIEVE: Sample-Efficient Parametric Learning from Natural Language

One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction

SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio

Memory Dial: A Training Framework for Controllable Memorization in Language Models

open-webui/open-webui

shiyu-coder/Kronos

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?

Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction