Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
Paper • 2606.00408 • Published • 64
AI & ML interests
None defined yet.
IPF
authored a
paper 4 months ago
IPF
submitted a
paper to Daily Papers 4 months ago
IPF
authored a
paper 5 months ago
IPF
authored a
paper 6 months ago
IPF
authored a
paper 7 months ago
lupantech
authored 2
papers 10 months ago
lupantech
authored 6
papers 12 months ago
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20
Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
Paper • 2506.15882 • Published • 2
Where LLM Agents Fail and How They can Learn From Failures
Paper • 2509.25370 • Published • 12
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs
Paper • 2509.22646 • Published • 17
TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
Paper • 2510.06217 • Published • 67
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Paper • 2510.05592 • Published • 113
lupantech
authored 7
papers over 1 year ago
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Paper • 2303.16199 • Published • 5
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Paper • 2304.09842 • Published • 2
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Paper • 2310.02255 • Published • 2
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Paper • 2304.15010 • Published • 4
Multimodal Procedural Planning via Dual Text-Image Prompting
Paper • 2305.01795 • Published • 1
TheoremQA: A Theorem-driven Question Answering dataset
Paper • 2305.12524 • Published • 1
Model Editing Can Hurt General Abilities of Large Language Models
Paper • 2401.04700 • Published • 3