Castuner

Unzip

Skyler @ LimitLess AI

Your guide to the latest AI and machine learning research. We unpack complex papers into actionable insights for practitioners and enthusiasts alike.

Listen in your app

Episodes

222 episodes

  1. Metacognitive Decoding: Efficient Inference for Diffusion Language Agents
  2. h1: A Taste of the Bitter Lesson in Automated Theorem Proving
  3. Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
  4. Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
  5. Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
  6. The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
  7. IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
  8. ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
  9. Training the Whole Agent, Not Just the Model
  10. Competence-Based Evaluation of Logical Reasoning in Large Language Models
  11. Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
  12. OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling
  13. 3DCodeVerse: Exploring 3D Worlds as Code
  14. Scalable Weak-to-Strong Verifier Hardening for Agent Environments
  15. Lluna: Collaborative Unimodal Models for Missing-Modality Inference
  16. Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs
  17. When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors
  18. Can machines reason non-verbally?
  19. Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics
  20. Pumpire: Unified Benchmark for Metric Distance Estimation
  21. OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
  22. Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
  23. DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
  24. Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
  25. 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
  26. SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
  27. Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
  28. Decoding Looped Transformers Better for (Almost) Free
  29. Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems
  30. Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
  31. Scaling Long-Form Story Generation via Narrative State Tracking
  32. IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking
  33. Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
  34. Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
  35. RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation
  36. FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
  37. Self-Evolving Search Index
  38. Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
  39. The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
  40. Thought without systematicity? Evaluating reasoning models on rule induction tasks
  41. Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
  42. Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2
  43. Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
  44. Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States
  45. Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
  46. Dr. Claw: An AI Scientist Workspace for Vibe Research
  47. The Attention Triangle in Audio-Video Models
  48. Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
  49. DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
  50. Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding