Ingrid Larsen

ingrid-l

·

AI & ML interests

LLM reasoning, chain-of-thought prompting, mathematical reasoning, tree-of-thought

Recent Activity

liked a dataset 8 days ago

agi-noobs/chess-sft-20k-llm-reasoning-enriched-dpo-hard-negatives-v1

liked a dataset 8 days ago

mlfoundations-dev/seed_code_self_consistency

liked a dataset 8 days ago

ticoAg/llm-complex-reasoning-train-qwen2-72b-instruct-correct

View all activity

Organizations

None yet

upvoted a paper 8 days ago

Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure

Paper • 2609.23551 • Published 19 days ago • 7

upvoted 5 papers 15 days ago

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 18 days ago • 157

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Paper • 2609.25001 • Published 18 days ago • 132

Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

Paper • 2609.20758 • Published 22 days ago • 4

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 496

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 21 days ago • 138

upvoted a paper 16 days ago

Learning Foresight without Explicit Trajectories for 3D Diffusion Policies

Paper • 2609.20669 • Published 22 days ago • 9

upvoted a paper 17 days ago

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published 23 days ago • 67

upvoted 2 papers 18 days ago

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 24 days ago • 78

SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization

Paper • 2609.14320 • Published 26 days ago • 34

upvoted a paper 19 days ago

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

Paper • 2609.16204 • Published 25 days ago • 4

upvoted 2 papers 20 days ago

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

Paper • 2609.05405 • Published Sep 4 • 45

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Paper • 2609.15972 • Published 25 days ago • 9

upvoted a paper 21 days ago

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

Paper • 2609.13680 • Published 27 days ago • 13