Paper Archive

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible per-object shapes, composing them yields scenes that collapse under physical simulation due to interpenetrating, hovering,...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction methods reduce this cost by evicting unimportant key-value pairs from the cache, yet they often yield worse accuracy than selection-based sparse atte...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are often smaller, less carefully curated, weakly documented, and rarely validated through controlled training experiments. W...

[object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can generate concrete visual rollouts of possible futures, while MLLMs can reason abstractly over questions, goals, and rules. How...

[object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstruction quality of a tokenizer does not necessarily translate into better generation quality, suggesting that latent representations should be evaluated ...

[object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

C_{11}H_9^+ ion is the dominant fragment cation formed from methyl-naphthalene (MeNp) and dimethyl-naphthalene (diMeNp). Using the multiplex capabilities of PIRENEA, a setup dedicated to laboratory astrophysics, we studied the reactivity of the benzylium-like isomers of C_{11}H_9^+ with diMeNp under...

[object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores. This single-metric paradigm presents a...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoTs naturally contain trial and errors and mainstream RLVR approaches choose outcome-correct CoT trajectories for memoriza...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Recently, diffusion models operating on VAE latents or mel-spectrograms have become the dominant paradigm for zero-shot TTS. Although these compressed representations improve generation efficiency, they inevitably suffer from information loss and non-end-to-end training. Theoretically, directly mode...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/2/2026 huggingface

Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NLI benchmarks are largely Western-centric, translation-derived, or monolingual, limiting their ability to measure culturally grounded reasoning. We i...