AI News — Latest Developments & Breakthroughs

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

arXiv:2601.10402v5 Announce Type: replace Abstract: The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimation

arXiv:2601.12410v2 Announce Type: replace Abstract: Cognitive anthropology suggests that the distinction of human intelligence lies in the ability to infer othe

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation

arXiv:2601.19178v2 Announce Type: replace Abstract: Sequential recommendation models are widely used in applications, yet they face stringent latency requiremen

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

CIRCLE: A Framework for Evaluating AI from a Real-World Lens

arXiv:2602.24055v4 Announce Type: replace Abstract: This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-c

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Agentified Assessment of Logical Reasoning Agents

arXiv:2603.02788v3 Announce Type: replace Abstract: We present a framework for evaluating and benchmarking logical reasoning agents when assessment itself must

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning

arXiv:2603.03072v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key chal

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics

arXiv:2603.11442v2 Announce Type: replace Abstract: Can humans detect AI-generated financial documents better than machines? We present GPT4o-Receipt, a benchma

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Relationship-Aware Safety Unlearning for Multimodal LLMs

arXiv:2603.14185v3 Announce Type: replace Abstract: Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation

arXiv:2603.21430v2 Announce Type: replace Abstract: Large language models (LLMs) have shown impressive capabilities in code generation. However, because most LL

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Human strategic decision making in parametrized games

arXiv:2104.14744v5 Announce Type: replace-cross Abstract: Many real-world games contain parameters which can affect payoffs, action spaces, and information stat

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Entire Space Counterfactual Learning for Reliable Content Recommendations

arXiv:2210.11039v3 Announce Type: replace-cross Abstract: Post-click conversion rate (CVR) estimation is a fundamental task in developing effective recommender

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data and LLMs Perspective

arXiv:2211.14997v5 Announce Type: replace-cross Abstract: Enterprise financial risk analysis aims at predicting the future financial risk of enterprises. Due to

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Perturbative adaptive importance sampling for Bayesian LOO cross-validation

arXiv:2402.08151v4 Announce Type: replace-cross Abstract: Importance sampling (IS) is an efficient stand-in for model refitting in performing (LOO) cross-valida

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Moonwalk: Inverse-Forward Differentiation

arXiv:2402.14212v2 Announce Type: replace-cross Abstract: Backpropagation's main limitation is its need to store intermediate activations (residuals) during the

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 6d ago

DIDLM: A SLAM Dataset for Difficult Scenarios Featuring Infrared, Depth Cameras, LIDAR, 4D Radar, and Others under Adverse Weather, Low Light Conditions, and Rough Roads

arXiv:2404.09622v3 Announce Type: replace-cross Abstract: Adverse weather conditions, low-light environments, and bumpy road surfaces pose significant challenge

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets

arXiv:2405.17573v3 Announce Type: replace-cross Abstract: We study Leaky ResNets, which interpolate between ResNets and Fully-Connected nets depending on an 'ef

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimation

arXiv:2407.01111v2 Announce Type: replace-cross Abstract: Heterogeneous treatment effect (HTE) estimation from observational data poses significant challenges d

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Dynamic Neural Potential Field: Online Trajectory Optimization in the Presence of Moving Obstacles

arXiv:2410.06819v3 Announce Type: replace-cross Abstract: Generalist robot policies must operate safely and reliably in everyday human environments such as home

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning

arXiv:2502.01521v4 Announce Type: replace-cross Abstract: Training reinforcement learning (RL) policies for legged locomotion often requires extensive environme

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Evaluation of Large Language Models via Coupled Token Generation

arXiv:2502.01754v3 Announce Type: replace-cross Abstract: State of the art large language models rely on randomization to respond to a prompt. As an immediate c

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control

arXiv:2503.11488v2 Announce Type: replace-cross Abstract: Adaptive traffic signal control (ATSC) is crucial in reducing congestion, maximizing throughput, and i

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

KINESIS: Motion Imitation for Human Musculoskeletal Locomotion

arXiv:2503.14637v3 Announce Type: replace-cross Abstract: How do humans move? Advances in reinforcement learning (RL) have produced impressive results in captur

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej

arXiv:2504.03486v2 Announce Type: replace-cross Abstract: Automating legal document drafting can improve efficiency and reduce the burden of manual legal work.

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries

arXiv:2504.09271v2 Announce Type: replace-cross Abstract: The ubiquity and widespread use of digital and online technologies have transformed mental health supp

⚡ AI-Lesson Articles