Latest AI/ML research from ArXiv and Papers with Code
Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has b...
Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking w...
Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite stron...
Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity...
Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on ...
We characterize the pre-softmax attention matrix QK^top in transformers as an associative memory matrix encoding pairwise associations between input features. By decomposing this m...
We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline v...
Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tamperin...
Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-l...
Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing par...
LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduc...
On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rollouts with a teacher model. Ho...
Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior fa...
The inverse problem of multilayer thin-film optical coatings design represents a complex combinatorial-continuous optimization challenge. We present PRISM (Position-encoded Regress...
Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-fine hierarchical generation. I...
Geometry estimation from perspective images has greatly advanced, maturing to the point where off-the-shelf foundation models are able to reconstruct 3D scene structure not only fr...
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as r...
Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and discrete diffusion models e...
End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing parad...
We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantiza...
Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain...
Interactive world models are advancing rapidly, yet existing benchmarks cover only part of the required competencies, leaving no unified standard for systematic evaluation. To fill...
Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate o...
Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to languag...