Focused Large Language Models are Stable Many-Shot Learners
Paper • 2408.13987 • Published
bitwxl
bitwxl2022
·
AI & ML interests
None yet
Recent Activity
authored a paper about 12 hours ago
Focused Large Language Models are Stable Many-Shot Learners authored a paper about 12 hours ago
Speculative Decoding for Multi-Sample Inference authored a paper about 12 hours ago
Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time ScalingOrganizations
authored 6
papers about 12 hours ago
Speculative Decoding for Multi-Sample Inference
Paper • 2503.05330 • Published
Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling
Paper • 2601.21684 • Published • 10
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
Paper • 2605.06110 • Published • 16
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
Paper • 2605.27030 • Published • 21
Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
Paper • 2506.15707 • Published
upvoted 2
papers about 12 hours ago
submitted a
paper to Daily Papers about 13 hours ago
liked a
Space over 1 year ago
authored 6
papers almost 2 years ago
BatchEval: Towards Human-like Text Evaluation
Paper • 2401.00437 • Published • 1
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
Paper • 2401.10480 • Published • 1
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
Paper • 2312.12832 • Published
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
Paper • 2407.02056 • Published • 2
Generative Dense Retrieval: Memory Can Be a Burden
Paper • 2401.10487 • Published
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
Paper • 2408.13457 • Published • 2
upvoted 3
papers almost 2 years ago
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
Paper • 2408.13457 • Published • 2
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
Paper • 2407.02056 • Published • 2
Internal Consistency and Self-Feedback in Large Language Models: A Survey
Paper • 2407.14507 • Published • 48