会员服务
Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents
Arxiv
0+阅读 · 10月15日
Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization
Arxiv
0+阅读 · 10月14日
Selection-Safe Conformal Early Exit: Distribution-Free Coverage under Adaptive Depth
Arxiv
0+阅读 · 10月14日
EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits Steering
Arxiv
0+阅读 · 10月15日
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
Arxiv
0+阅读 · 10月14日
Stateful Testing for Deep Learning Compilers
Arxiv
0+阅读 · 10月15日
MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference
Arxiv
0+阅读 · 10月15日
Testing and Verification of Quantum Compilers through Assurance Contracts and Evidence
Arxiv
0+阅读 · 10月14日
Coverage Region Analysis and Optimization of FIRES-Assisted NOMA and OMA Systems
Arxiv
0+阅读 · 10月15日
KoViDoRe: A Benchmark for Korean Visual Document Retrieval
Arxiv
0+阅读 · 10月15日
Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design
Arxiv
0+阅读 · 10月15日
Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction
Arxiv
0+阅读 · 10月15日
SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis
Arxiv
0+阅读 · 10月14日
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
Arxiv
0+阅读 · 10月15日
Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Arxiv
0+阅读 · 10月15日
参考链接
微信扫码咨询专知VIP会员
Top