-
E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
score 4
入选 HF Daily Papers；关键词(3): fine-tuning, reasoning, vision-language
-
What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements
score 4
机构: NVIDIA；关键词(2): latency, edge
-
Communication-Efficient LLM Adaptation over Decentralized GPU Meshes
score 4
机构: Amazon；关键词(3): compression, throughput, pretraining
-
Question's Gambit: The First Move Matters in Agentic Deep Search
score 4
机构: University of Toronto；关键词(3): RAG, agentic, reasoning
-
Sharing standardized image-derived data in computational pathology using DICOM
score 4
机构: Google；关键词(1): open-source
-
TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendation
score 4
关键词(2): latency, reasoning；顶会接收: EMNLP
-
Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation
score 4
机构: Cambridge；关键词(2): distillation, deployment
-
Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
score 4
关键词(3): agentic, reasoning, vision-language；顶会接收: EMNLP
-
Building Legal Reward Models for Grounding and Abstention
score 4
机构: EPFL；关键词(4): DPO, retrieval-augmented, RAG, reasoning
-
Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models
score 4
关键词(3): post-training, reasoning, open-source；顶会接收: EMNLP
-
Exploring Multimodal Turn-Taking Cues in Face-to-Face Conversation using Voice Activity Projection
score 3
顶会接收: EMNLP
-
The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation
score 3
机构: University of Washington