6/ Efficient LLM Inference – proposes a layer-condensed KV cache to achieve efficient inference in LLMs; only computes and caches the key-values (KVs) of a small number of layers which leads to saving memory consumption and improved inference throughput.
@dair_ai
-
Guide for Evaluating Large Language Models with Open-Source Library
By
–
7/ Guide for Evaluating LLMs – provides guidance and lessons for evaluating large language models; discusses challenges and best practices, along with the introduction of an open-source library for evaluating LLMs.
-
How Far Are We From Achieving AGI
By
–
5/ How Far Are We From AGI – presents an opinion paper addressing important questions to understand the proximity to artificial general intelligence (AGI).
-
Hierarchical Reasoning Aggregation Framework for LLM Answer Selection
By
–
4/ Enhancing Answer Selection in LLMs – proposes a hierarchical reasoning aggregation framework for improving the reasoning capabilities of LLMs; the approach selects answers based on the evaluation of reasoning chains.
-
Open-Source Generative AI: Balancing Risks and Opportunities
By
–
3/ Risks and Opportunities of Open-Source Generative AI – analyzes the risks and opportunities of open-source generative AI models; argues that the overall benefits of open-source generative AI outweigh its risks.
-
Agent Planning with World Knowledge Model for Advanced AI
By
–
2/ Agent Planning with World Knowledge Model – a parametric world knowledge model to facilitate agent planning; the agent model can self-synthesize knowledge from expert and sampled trajectories; this is used to train the world knowledge model.
-
IBM Releases Granite Code Models Across 116 Programming Languages
By
–
10). Granite Code Models – introduce Granite, a series of code models trained with code written in 116 programming languages; it consists of models ranging in size from 3 to 34 billion parameters, suitable for applications ranging from application modernization tasks to on-device
-
World Models Survey: Generative Video Synthesis Methodologies Overview
By
–
8). Survey of General World Models – presents an overview of generative methodologies in video generation, where world models facilitate the synthesis of highly realistic visual content.
-
MAmmoTH2: Harvesting Web Data to Enhance LLM Reasoning
By
–
9). MAmmoTH2 – harvest 10 million naturally existing instruction data from the pre-training web corpus to enhance LLM reasoning; the approach first recalls relevant documents, extracts instruction-response pairs, and then refines the extracted pairs using open-source LLMs;
-
Consistency LLMs: Parallel Decoders Reduce Inference Latency
By
–
6). Consistency LLMs – uses efficient parallel decoders that reduce inference latency by decoding n-token sequence per inference step; inspired by he human's ability to form complete sentences before articulating word by word…