Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
Paper • 2605.09630 • Published • 1
SambaNova
company
Verified
Inference Provider
VERIFIED
21,997 monthly requests
AI & ML interests
None defined yet.
Recent Activity
View all activity
linzheng
submitted a
paper to Daily Papers 13 days ago
hongfenglu
authored a
paper about 2 months ago
linzheng
submitted a
paper to Daily Papers 4 months ago
ravir123
authored 2
papers 4 months ago
xl-zhao
authored a
paper 6 months ago
hongfenglu
authored 4
papers 7 months ago
Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
Paper • 2503.07807 • Published • 1
On the Tool Manipulation Capability of Open-source Large Language Models
Paper • 2305.16504 • Published • 2
Synthetic Document Question Answering in Hungarian
Paper • 2505.23008 • Published
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 132
xl-zhao
authored 10
papers 8 months ago
VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions
Paper • 2305.18756 • Published
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Paper • 2402.13577 • Published • 9
There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
Paper • 2204.02624 • Published
GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
Paper • 2402.19255 • Published • 1
There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning
Paper • 2210.12459 • Published
Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation
Paper • 2210.12460 • Published
Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure
Paper • 2210.12461 • Published
SubgoalXL: Subgoal-based Expert Learning for Theorem Proving
Paper • 2408.11172 • Published
Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
Paper • 2410.16736 • Published • 1
PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models
Paper • 2503.02324 • Published