Carnegie Mellon University

CarnegieMellonU's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

VanishD 

authored a paper 13 days ago

Generalizable End-to-End Tool-Use RL with Synthetic CodeGym

Paper • 2509.17325 • Published Sep 22 • 1

ethanning 

authored a paper 2 months ago

Less LLM, More Documents: Searching for Improved RAG

Paper • 2510.02657 • Published Oct 3 • 2

xiaofanghf 

authored 2 papers 4 months ago

Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision

Paper • 2507.20976 • Published Jul 28 • 10

Aligning Medical Images with General Knowledge from Large Language Models

Paper • 2409.00341 • Published Aug 31, 2024 • 2

LDA1020 

authored 8 papers 6 months ago

Functional Interpolation for Relative Positions Improves Long Context Transformers

Paper • 2310.04418 • Published Oct 6, 2023 • 4

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

Paper • 2106.12566 • Published Jun 23, 2021

Can Vision Transformers Perform Convolution?

Paper • 2111.01353 • Published Nov 2, 2021

Your Transformer May Not be as Powerful as You Expect

Paper • 2205.13401 • Published May 26, 2022 • 1

An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

Paper • 2408.00724 • Published Aug 1, 2024 • 1

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

Paper • 2504.04310 • Published Apr 6

TFG-Flow: Training-free Guidance in Multimodal Generative Flow

Paper • 2501.14216 • Published Jan 24

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

Paper • 2505.08783 • Published May 13 • 1

jacobyeung 

authored a paper 6 months ago

Neural Representations of Dynamic Visual Stimuli

Paper • 2406.02659 • Published Jun 4, 2024

ZMC2019 

authored 7 papers 6 months ago

SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification

Paper • 2305.09781 • Published May 16, 2023 • 4

GNNPipe: Scaling Deep GNN Training with Pipelined Model Parallelism

Paper • 2308.10087 • Published Aug 19, 2023 • 1

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Paper • 2402.12374 • Published Feb 19, 2024 • 4

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Paper • 2404.11912 • Published Apr 18, 2024 • 17

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

Paper • 2406.02532 • Published Jun 4, 2024 • 13

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Paper • 2408.11049 • Published Aug 20, 2024 • 13

MINI-SEQUENCE TRANSFORMER: Optimizing Intermediate Memory for Long Sequences Training

Paper • 2407.15892 • Published Jul 22, 2024