Bongard: Training Machine Intuition
cs.CL
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/AgentBull/bongard
Project page: https://mohit67890.github.io/imajev/report
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Program Synthesis with Large Language Models
- Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Training Deep Nets with Sublinear Memory Cost
- Training Verifiers to Solve Math Word Problems
- Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
- Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Flex Attention: A Programming Model for Generating Optimized Attention Kernels
- Gemma 3 Technical Report
- BERT-JEPA: Reorganizing CLS Embeddings for Language-Invariant Semantics
- LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- FP8 Formats for Deep Learning
- Pretraining Large Language Models with NVFP4
- RWKV-7 "Goose" with Expressive Dynamic State Evolution
- Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering