Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
Compares PEFT methods (LoRA, QLoRA, BitFit etc.) plus a new adaptive checkpointing strategy on ViT/Mamba vision models and VLMs, showing 20-30% energy cuts and 43-79% memory reduction at small accuracy cost on CIFAR-100/DTD.
SPIKER-LL extends the open-source Spiker+ SNN accelerator with microarchitectural support for the STSF local learning rule, delivering up to 93% accuracy, sub-millisecond latency, and under 0.1 mJ per inference on MNIST variants while remaining DSP-free.
citing papers explorer
-
Language-Conditioned Visual Grounding with CLIP Multilingual
Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
-
Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs
Compares PEFT methods (LoRA, QLoRA, BitFit etc.) plus a new adaptive checkpointing strategy on ViT/Mamba vision models and VLMs, showing 20-30% energy cuts and 43-79% memory reduction at small accuracy cost on CIFAR-100/DTD.
-
Spiker-LL: An Energy-Efficient FPGA Accelerator Enabling Adaptive Local Learning in Spiking Neural Networks
SPIKER-LL extends the open-source Spiker+ SNN accelerator with microarchitectural support for the STSF local learning rule, delivering up to 93% accuracy, sub-millisecond latency, and under 0.1 mJ per inference on MNIST variants while remaining DSP-free.