Topics
Results for “gnm”
36 results
- NousResearch/Arete-27B — Hugging Face Models · Seen
- Solve a full course assignment with a coding agent — Agent Use Cases · Seen
- myned-ai/Ava256-FLAME-GNM — Hugging Face Datasets · Seen
- Alignment with Reflect-Reasoning: Learning How To Follow Principles — arXiv AI Papers · Seen
- SWAM: Scaling World Action Models with Cross-Modal Alignment — Hugging Face Papers · Seen · 24 points
- What Do Tokenizer Comparisons Measure? Disentangling Granularity, Root Assignment, and Word-Level Readout across Amharic and Hausa — arXiv AI Papers · Seen
- Graph Label Alignment: A Diagnostic Atlas for Graph Classification — arXiv AI Papers · Seen
- TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption — arXiv AI Papers · Seen
- Not All Misalignment Is Alike: A Decomposed Benchmark for Emergent Misalignment — arXiv AI Papers · Seen
- Quiz yourself and grade assignments against rubrics as a student — Agent Use Cases · Seen
- Perceptual Distortion for Overfitted Video Coding: Sliced Matching in Space, Error Alignment in Time — arXiv AI Papers · Seen
- Server-Side Sparse Assignment for Federated Mixture-of-Experts — arXiv AI Papers · Seen
- Objective-Conditioned Active Preference Learning for Multi-Objective Alignment — arXiv AI Papers · Seen
- Alignment Faking Depends on the Value, Not Just the Model — arXiv AI Papers · Seen
- SemaNorm: Stain Normalization via Semantic and Morphology Alignment for Robust Cross-Hospital Computational Pathology — arXiv AI Papers · Seen
- witness-archive/alignment-hub — Hugging Face Spaces · Seen
- We ran AI agent swarms in Minecraft and Mindustry — Hacker News · Seen · 420 points
- How we detect frontier model misalignment — OpenAI Blog · Seen
- Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment — arXiv AI Papers · Seen
- Dayjob: Tax – evaluating AI agents on 50 professional tax assignments — Hacker News · Seen · 260 points
- ProtoEEG: Structured Prototype Alignment for EEG Visual Decoding — arXiv AI Papers · Seen
- EKT-Router: Expert-Evidence Alignment for Embodied Vision-Language Models — arXiv AI Papers · Seen
- Distributional Alignment of LLMs and Its Generalization Properties — arXiv AI Papers · Seen
- An alignment assessment of the UK AISI cybertesting incident — Hacker News · Seen · 18 points
- Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback — arXiv AI Papers · Seen
- GeoForward: Geometry-Guided Cross-View Alignment for Feedforward 3D Gaussian Splatting — arXiv AI Papers · Seen
- Translating in style: An open-weight alternative to GPT-4 for culturally aligned machine translation — arXiv AI Papers · Seen
- HeRE: A Novel Benchmark for Hebrew Relation Extraction via LLM-Guided Denoising of Knowledge Graph Alignments — arXiv AI Papers · Seen
- Progressive Misalignment Can Emerge from Benign Recursive Self-Distillation — arXiv AI Papers · Seen
- Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech — arXiv AI Papers · Seen
- Purify Before You Align: Improving Representation Alignment for Diffusion Models — arXiv AI Papers · Seen
- OpenAssistant/oasst1 — Hugging Face Datasets · Seen
- Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment — arXiv AI Papers · Seen
- Lag: A Mean-Field Optimal Policy for Online Assignment with Reusable Resources — arXiv AI Papers · Seen
- Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment — arXiv AI Papers · Seen
- An Open Letter on AI and Cybersecurity from the Scientific Community — Hacker News · Seen · 10 points