Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward ...
System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt age...
Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large l...
Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many such problems require imagina...
Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still grows with sequence length, an...
Instruction-guided speech editing requires a model to modify specified speech attributes while preserving unrelated characteristics. Despite rapid progress in Speech Large Language...
Learning representations of CAD models is a largely open problem. While 3D representation learning has flourished around point clouds and meshes, the native format of CAD - boundar...
Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model chan...
Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifac...
LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate thi...
Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel,...
Muon improves training efficiency over Adam in large language-model training by about two times, but the local geometric source of this advantage remains unclear. Our work takes a ...
Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit latent biases in t...
Reinforcement learning with verifiable rewards (e.g. GRPO) is now a common way to improve mathematical reasoning in Large Language Models (LLMs). However, current methods usually b...
Large language models (LLMs) are increasingly proposed as clinical agents, yet static, single-turn benchmarks cannot capture how a model dynamically delivers care across an encount...
Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, vis...
Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next-level capability: whether m...
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 e...
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 o...
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can genera...
Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoT...
Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page...
Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existing adaptive sampling methods ...
A core goal of computational social science is to discover interpretable differences in how language varies across outcomes of interest, such as political affiliation or instructio...