arXiv AI
LLM2R: From Large Language Models to 3D Reassemblers
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
2d ago
3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
arXiv:2606.19828v2 Announce Type: replace Abstract: 3D multimodal large language models (3D MLLMs) describe a 3D object as a whole but cannot address, name, or reason about its parts. Prior part-awar...
arXiv AI
Sep 10
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
A*-Thought-V2 is a framework that models Chain-of-Thought reasoning as a geometric trajectory in a 3D PCA space, using explicit-implicit latent tokens to compress steps that deviate from the main question-to-solution direction. The method measures alignment angles to decide which steps remain text and which become latent, and introduces stepwise embedding forcing and label forcing to train the architecture. Experiments on Qwen models show up to 2.6% accuracy gains, halved response length, and significant reductions in computation and training time.
arXiv AI
Oct 27
NGM: A Plug-and-Play Training-Free Memory Module for LLMs
arXiv:2605.16893v2 Announce Type: replace Abstract: Recent studies have introduced memory-augmented architectures that decouple knowledge storage from neural computation, enabling more direct access...
arXiv Machine Learning
Sep 17
Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
Subspace-Decomposed JEPAs (SD-JEPA) split the latent space of Joint-Embedding Predictive Architectures into two orthogonal subspaces: a low-dimensional progression subspace trained with a cosine-margin triplet loss and a high-dimensional content subspace regularised by SIGReg. The authors prove that the anti-collapse forces act on disjoint coordinates, allowing additive composition rather than competition. SD-JEPA outperforms the LeWM baseline on most control benchmarks and the strongest non-LeWM JEPA baseline on Push‑T, with a subspace-ablation confirming the split as essential. The 1‑D angular progression coordinate serves as a scene-aware compass, advancing with task progress, regressing on backtracking, and relocalising under perturbations to separate surprise from meaning.
arXiv Machine Learning
Aug 31
DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
The paper introduces DARTS, a method for tuning decoder representations during model merging. It addresses representation bias in autoregressive decoders by using an entropy‑weighted L1 loss and a per‑position additive bias to correct errors that accumulate across token positions. Experiments on code generation, mathematical reasoning, and instruction following with Llama‑2‑7B show that DARTS improves performance over standard surgery while adding only 0.1% extra parameters.
arXiv Computer Vision
Aug 25
BIMScript: Material-Aware Structured Scene Programs for BIM Ingestion
arXiv:2608.21447v1 Announce Type: new Abstract: Structured-language models such as SceneScript reconstruct a scene as a short program of parametric commands, an inherently editable and semantically e...