IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 6polarities
background 2representative citing papers
Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
SHARP applies a spectrum-aware dynamic RoPE scaling schedule that promotes resolution more strongly in early denoising stages and relaxes it later, outperforming static baselines on quality metrics for remote sensing images.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
PointNTP serializes point clouds into geometry-ordered patch sequences and applies causal next-token prediction with stop-gradient targets for decoder-free self-supervised pre-training, reporting competitive results on ScanObjectNN, ShapeNetPart, and S3DIS.
RoTE is a multi-level rotary time embedding module that explicitly models time spans in sequential recommendation and improves NDCG@5 by up to 20.11% when added to standard backbones on public benchmarks.
citing papers explorer
-
LLM Translation of Compiler Intermediate Representation
IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
-
Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation
Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
-
SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis
SHARP applies a spectrum-aware dynamic RoPE scaling schedule that promotes resolution more strongly in early denoising stages and relaxes it later, outperforming static baselines on quality metrics for remote sensing images.
-
Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
-
Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework
PointNTP serializes point clouds into geometry-ordered patch sequences and applies causal next-token prediction with stop-gradient targets for decoder-free self-supervised pre-training, reporting competitive results on ScanObjectNN, ShapeNetPart, and S3DIS.
-
RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation
RoTE is a multi-level rotary time embedding module that explicitly models time spans in sequential recommendation and improves NDCG@5 by up to 20.11% when added to standard backbones on public benchmarks.