Search Results for author:
Found 8 papers, 6 papers with code
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effortlessly process many originally exhausting tasks -- e. g., digesting a long-form document to find answers vs. directly asking an LLM about it.
SELF: Self-Extend the Context Length With Logistic Growth Function
Large language models suffer issues when operated on long contexts that are larger than their training context length due to the standard position encoding for tokens in the attention layer.
Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient long-context capacity, motivated by empirical observations such as (1) higher context window length often leads to stronger reasoning performance, and (2) failed reasoning cases resemble failed long-context cases.
Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
Moreover, when applied to a non-reasoning model (Qwen-2. 5-7B-Instruct), our framework boosts its accuracy from 74. 0% to 81. 8% on the same benchmark, achieving a relative improvement of 7. 8%.
Thinking Preference Optimization
To further boost the performance with the SFT data, we propose Thinking Preference Optimization (ThinkPO), a simple yet effective post-SFT method that enhances long CoT reasoning without requiring new long CoT responses.
Linear building pattern recognition via spatial knowledge graph
First, we use the property graph to express the spatial relations in proximity, similar and linear arrangement between buildings; secondly, the rules of linear pattern recognition are expressed as the rules of knowledge graph reasoning; finally, the linear building patterns are recognized by using the rule-based reasoning in the built knowledge graph.
Stabilizing the Maximal Entropy Moment Method for Rarefied Gas Dynamics at Single-Precision
This paper aims to stabilize MEM, making it possible to simulating very strong normal shock waves on modern GPUs at single precision.
Advbox: a toolbox to generate adversarial examples that fool neural networks
In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance.
