A Neuroscience-Inspired Dual-Process Model of Compositional Generalization
Paper • 2507.18868 • Published • 1
Urro PRO
urroxyz
AI & ML interests
computational linguistics major
Recent Activity
updated a collection about 7 hours ago
HUMAN-WRITTEN & LEGALLY-SOURCED* liked a dataset about 7 hours ago
th1nhng0/vietnamese-legal-documents updated a collection about 8 hours ago
WTF GENIUS PAPERSOrganizations
upvoted 9
papers about 8 hours ago
LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
Paper • 2310.15164 • Published • 4
JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation
Paper • 2512.19171 • Published • 1
Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers
Paper • 2210.11265 • Published • 1
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
Paper • 2603.07461 • Published • 1
Interpretable-by-Design Transformers via Architectural Stream Independence
Paper • 2603.07482 • Published • 1
Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
Paper • 2506.13331 • Published • 1
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Paper • 2505.15257 • Published • 1
Are formal and functional linguistic mechanisms dissociated in language models?
Paper • 2503.11302 • Published • 1
upvoted 11
papers 1 day ago
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Paper • 2601.07372 • Published • 47
The Universal Normal Embedding
Paper • 2603.21786 • Published • 9
Generalized Discrete Diffusion from Snapshots
Paper • 2603.21342 • Published • 11
REVERE: Reflective Evolving Research Engineer for Scientific Workflows
Paper • 2603.20667 • Published • 14
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
Paper • 2603.21383 • Published • 13
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
Paper • 2603.18118 • Published • 10
Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels
Paper • 2603.22276 • Published • 10
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Paper • 2603.19028 • Published • 16
BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
Paper • 2603.20309 • Published • 18
Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection
Paper • 2603.21944 • Published • 25
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models
Paper • 2603.21341 • Published • 22