Paper Citation Record · LEDGER

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge

As of 21 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2505.10782.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.10782 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:08:59.967867Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy19
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e55f02d6-a953-4b4d-9b8e-e3beb00f404d · outbound

This paper cites A survey on multimodal large language models for autonomous driving,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge A survey on multimodal large language models for autonomous driving,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.809601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cda135b1-e89e-4f4b-b5be-afd144536842 · outbound

This paper cites Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.720640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aead2e63-f361-4274-863c-3d6b06a59632 · outbound

This paper cites MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.727174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4623e4ae-0f1e-42c5-82b0-576452019351 · outbound

This paper cites SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.732942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fe0d4e6-1d74-4c57-94cd-108dcb718945 · outbound

This paper cites Lmdrive: Closed-loop end-to-end driving with large language models,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Lmdrive: Closed-loop end-to-end driving with large language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.793113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d46bef63-fdbc-4467-a617-0be21a7cf847 · outbound

This paper cites A 17–95.6 tops/w deep learning inference accelerator with per-vector scaled 4-bit quantization for transformers in 5nm,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge A 17–95.6 tops/w deep learning inference accelerator with per-vector scaled 4-bit quantization for transformers in 5nm,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.774986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1d0e7c6c-7e23-4aa3-9fb8-dc48e6c0de77 · outbound

This paper cites 22.9 a 12nm 18.1tflops/w sparse transformer processor with entropy-based early exit, mixed-precision predication and fine- grained power management,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge 22.9 a 12nm 18.1tflops/w sparse transformer processor with entropy-based early exit, mixed-precision predication and fine- grained power management,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.758379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 161bdf0d-3d26-4b69-ab4f-c2bce746c1ba · outbound

This paper cites Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.740407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3dc86209-cda5-4417-b3d1-c6aaf9c23707 · outbound

This paper cites A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.761887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adad00e-19b0-4674-b99f-2c9c4a187636 · outbound

This paper cites Blueface: Integrating an accelerator into the core’s pipeline through algorithm-interface co- design for real-time socs,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Blueface: Integrating an accelerator into the core’s pipeline through algorithm-interface co- design for real-time socs,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.722879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fb586d93-5528-483d-a2c5-2523dfc57b67 · outbound

This paper cites an unresolved cited work.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:09:00.704454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 57570916-7428-4481-b528-76f2cf8781b0 · outbound

This paper cites Sapphire rapids: The next-generation intel xeon scal- able processor,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Sapphire rapids: The next-generation intel xeon scal- able processor,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.686065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e905ebb0-9a45-46f0-9863-7d5dbb4a2718 · outbound

This paper cites Intel accelerators ecosystem: An soc-oriented perspec- tive,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Intel accelerators ecosystem: An soc-oriented perspec- tive,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.667335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc29c1cc-28f4-47b7-87ce-e23ad534cb5c · outbound

This paper cites an unresolved cited work.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:09:00.650174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 82167fdd-592e-4584-9668-ca31e1ea78b1 · outbound

This paper cites an unresolved cited work.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:09:00.633246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2d14b5a9-cbbf-41c6-a4c1-906ef83fa017 · outbound

This paper cites Generative multimodal models are in-context learners,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Generative multimodal models are in-context learners,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.615188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 866eb2e2-1079-44cf-94ea-4e0cb73e7baa · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.808197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a12e346-7b85-4170-ad92-d39e3cb2f4a0 · outbound

This paper cites Visual instruction tuning,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Visual instruction tuning,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.814071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ae4d48e-a35c-46a7-8eac-13de2b1a7c29 · outbound

This paper cites Learning transferable visual models from natural lan- guage supervision,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Learning transferable visual models from natural lan- guage supervision,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.587567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0b05c7d3-efd1-45d2-a106-34ba268cf450 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.564547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6c6a3cb5-88f0-4d77-a250-f7c3b484f8c2 · outbound

This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.831451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca995e71-5c60-4969-b821-c0713ddc9d8d · outbound

This paper cites TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.838409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5147dd3e-fd12-45db-9c20-ddce0372dc7f · outbound

This paper cites Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.546354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3575af4b-7605-4411-83c5-3e6506ed4e46 · outbound

This paper cites Phi-2: The surprising power of small language models,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Phi-2: The surprising power of small language models,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.528956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a5a5f427-2944-4b03-a669-1447ad160854 · outbound

This paper cites SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.857272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a783c36-ba94-4b8e-ae3b-aad1f24327da · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge DINOv2: Learning Robust Visual Features without Supervision

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.863419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23c43ede-cecf-4d68-af09-7ba35291d5c2 · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge TinyLlama: An Open-Source Small Language Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.868956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b77d90fc-1d5d-40cc-9353-0bf4d8fbbf44 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.875147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8295163a-a213-4db5-963c-61f385158b1e · outbound

This paper cites Sigmoid loss for language image pre-training,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Sigmoid loss for language image pre-training,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.510211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f96309bf-cd65-4706-9331-90fbaf0bf08e · outbound

This paper cites https://github.com/ thomas-yanxin/KarmaVLM, 2024.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge https://github.com/ thomas-yanxin/KarmaVLM, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.489811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b2a0ca01-25f1-4766-ba57-f4c56656a1c4 · outbound

This paper cites Qwen Technical Report.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Qwen Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.892636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef0f008-4fa6-475f-a89b-d4c157af22df · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Gemini: A Family of Highly Capable Multimodal Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.898445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef85ef08-1a8b-4e70-9339-24a237432a0e · outbound

This paper cites GPT-4 Technical Report.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge GPT-4 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.903769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78725f1d-e0bf-42ce-946a-fbe3abc9bb12 · outbound

This paper cites Improved baselines with visual instruction tuning,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Improved baselines with visual instruction tuning,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.471529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 219f60f8-56c6-49ca-b9b1-9e05988ca4f6 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Making the v in vqa matter: Elevating the role of image understanding in visual question answering,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.454477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4bb86683-20f2-4da2-a08b-8ac1e9a97d78 · outbound

This paper cites Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.920456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79832185-419b-4fca-9fbc-6914c248d28d · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.926535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b8eb96-e791-404e-b5b9-44da71fda8fa · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Mmbench: Is your multi-modal model an all-around player?,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.436610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c6e26bd-44e7-482e-a6d7-a681543d02d7 · outbound

This paper cites Full Stack Optimization of Transformer Inference: a Survey.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Full Stack Optimization of Transformer Inference: a Survey

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.936655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6155361e-0497-41fb-a760-0cae93f7bba8 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.942603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90573873-29e0-4b58-b210-a46426deb9b7 · outbound

This paper cites Mistral 7B.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Mistral 7B

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.947708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09713d9d-77da-4c53-96fc-2cb8ec13a748 · outbound

This paper cites H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.953094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc40dc13-eed7-4148-af70-118779202a62 · outbound

This paper cites Snitch: A tiny pseudo dual-issue processor for area and energy efficient execution of floating- point intensive workloads,.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge Snitch: A tiny pseudo dual-issue processor for area and energy efficient execution of floating- point intensive workloads,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:09:00.418905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d9527fc6-078b-4862-b21d-97325a75440d · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge A Simple and Effective Pruning Approach for Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.962787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23625ce6-77f0-4e34-b78c-111930edb60d · outbound

This paper cites CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models.

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:59.967867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.