Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model Paper • 2611.14418 • Published 6 days ago • 5
Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents Paper • 2608.22237 • Published 9 days ago • 23 • 12
Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents Paper • 2608.22237 • Published 9 days ago • 23 • 12
Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents Paper • 2608.22237 • Published 9 days ago • 23 • 12
SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering Paper • 2611.13410 • Published 6 days ago • 41
Position: Categorical Deep Learning is an Algebraic Theory of All Architectures Paper • 2402.15332 • Published Feb 23, 2024 • 2 • 1
Position: Categorical Deep Learning is an Algebraic Theory of All Architectures Paper • 2402.15332 • Published Feb 23, 2024 • 2
Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model Paper • 2611.13425 • Published 6 days ago • 3
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation Paper • 2502.09838 • Published Feb 14, 2025 • 11
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space Paper • 2505.15778 • Published May 21, 2025 • 20 • 4
Tree-Ising: Repairing Language Models with Bit-Level Ising Edits Paper • 2611.14210 • Published 6 days ago • 47
Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages Paper • 2611.10304 • Published 9 days ago • 24
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? Paper • 2611.08175 • Published 11 days ago • 44 • 8
Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost Paper • 2611.03852 • Published 14 days ago • 19
Tools Need Not Speak in Text: Latent Context Compression for Agents Paper • 2611.06500 • Published 12 days ago • 9
OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery Paper • 2610.37739 • Published 20 days ago • 8
Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories Paper • 2611.02244 • Published 15 days ago • 16