Topics
Results for “reasoning”
37 results
- Hybrid Reasoning Agents: 35–55% fewer tokens and up to 2.6× faster inference — 2 sources · Seen · 506 points
- nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 — Hugging Face Models · Seen
- inclusionAI/Ling-3.1-flash — Hugging Face Models · Seen
- StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions — Hugging Face Papers · Seen · 20 points
- 3DCodeVerse: Exploring 3D Worlds as Code — Hugging Face Papers · Seen · 114 points
- nvidia/Nemotron-SFT-Finance-Document-Grounded-Reasoning-v1 — Hugging Face Datasets · Seen
- TIGER-Lab/MMLU-Pro — Hugging Face Datasets · Seen
- openai/gsm8k — Hugging Face Datasets · Seen
- MoreThought/Fable-5.1-Max-Reasoning-Filtered-10000x — Hugging Face Datasets · Seen
- Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs — arXiv AI Papers · Seen
- Latent Multimodal Memory Reasoning — arXiv AI Papers · Seen
- Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks — arXiv AI Papers · Seen
- Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning — arXiv AI Papers · Seen
- PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents — arXiv AI Papers · Seen
- From Events to Reasoning: Hierarchical Rule Composition over Explicit States — arXiv AI Papers · Seen
- open-thoughts/OpenThoughts3-1.2M — Hugging Face Datasets · Seen
- nvidia/OpenCodeReasoning — Hugging Face Datasets · Seen
- NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning — NVIDIA Developer Blog · Seen
- Trust in Depth: Giving agents more autonomy without losing control — AWS Machine Learning Blog · Seen
- Pattern Matching Beats Narrative Reasoning — Hacker News · Seen · 50 points
- ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models — arXiv AI Papers · Seen
- AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks — arXiv AI Papers · Seen
- CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models — arXiv AI Papers · Seen
- AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens — arXiv AI Papers · Seen
- Gemini 4 Argon for Robotics — Google DeepMind Blog · Seen
- Dev Opportunity Radar #20: $2M AI Reasoning Challenge, PayPal AI Hackathon, and Coinbase Analytics Challenge — DEV Community · Seen
- open-thoughts/OpenThoughts-114k — Hugging Face Datasets · Seen
- Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping — Hugging Face Papers · Seen · 29 points
- Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming — arXiv AI Papers · Seen
- Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models — arXiv AI Papers · Seen
- Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data — arXiv AI Papers · Seen
- Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning — arXiv AI Papers · Seen
- Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures — arXiv AI Papers · Seen
- SpatialASM: Internalizing Active Mentalization for Spatial Reasoning — Hugging Face Papers · Seen · 18 points
- ScaleAI/HSS — Hugging Face Datasets · Seen
- Gemini 4 Argon for Robotics — Hacker News · Seen · 219 points
- ryanmarten/OpenThoughts-1k-sample — Hugging Face Datasets · Seen