ArgBench unifies 33 existing datasets into a standardized benchmark for testing LLMs across 46 argumentation tasks and analyzes the impact of prompting techniques and model factors on performance.
hub
GQA : Training generalized multi-query transformer models from multi-head checkpoints
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
SAGA introduces workflow-atomic scheduling for compound AI agents, achieving 1.64x lower task completion time and 1.22x better memory utilization than vLLM on a 64-GPU cluster at the cost of 30% lower peak throughput.
Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.
MosaicKV achieves up to 16x attention speedup, 4.8x lower decode latency, 7.3x higher throughput, and 3x memory reduction with 1.76% accuracy loss via dynamic two-D KV cache compression and management on H800 GPUs.
LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
QK Product Steering suppresses dominant singular modes in the per-head QK product of selected middle layers via a closed-form query-only update, yielding 4.0% average relative CHAIR_s reduction on three GQA VLMs.
Priming transfers knowledge from pre-trained Transformers to hybrid SSM-attention models, recovering performance with minimal additional tokens and showing Gated KalmaNet outperforming Mamba-2 on long-context reasoning at 32B scale.
EpiCache clusters long conversation history into coherent episodes for per-episode KV cache eviction, delivering up to 30% accuracy gains and 3.7x peak memory reduction on LongConvQA tasks under fixed budgets.
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
MOSAIC uses an Integer Linear Program scheduler for expert placement and prompt assignment plus adaptive aggregation to achieve 1.7-2.3x end-to-end speedup on 4-GPU MoA workloads while keeping accuracy within 0.1pp.
MATCH augments sparsified attention with an efficient in-context retrieval system to boost performance on long-range recall tasks in transformers.
citing papers explorer
-
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
SAGA introduces workflow-atomic scheduling for compound AI agents, achieving 1.64x lower task completion time and 1.22x better memory utilization than vLLM on a 64-GPU cluster at the cost of 30% lower peak throughput.
-
Priming: Hybrid State Space Models From Pre-trained Transformers
Priming transfers knowledge from pre-trained Transformers to hybrid SSM-attention models, recovering performance with minimal additional tokens and showing Gated KalmaNet outperforming Mamba-2 on long-context reasoning at 32B scale.