Latest AI/ML research from ArXiv and Papers with Code
LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a s...
A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth est...
Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Quest...
While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to ...
A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians, ...
Current models of representational reliability in neural populations focus on temporal stability: whether population centroids are preserved across sessions and days. This framing ...
Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of f...
We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual sc...
People overthink; language models over-sample, and the extra effort can talk both into a worse answer. Reasoning systems answer a hard question by sampling it many times (test-time...
LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable...
Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture? Large Language Models (LLMs) integrated into evolutionary search h...
High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (triggering) under tight constraints on bandwidth, latency, and storage....
Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science....
Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains on the target distribution come at the cost of the foundation mo...
We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from h...
Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events i...
To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can accomplish lossless memory reduction on ...
Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pip...
Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on c...
Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward ...
Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches, avoiding discrete tokenization or a separately pretrained toke...
RocketSmith is an agentic system which intelligently automates the DFAM process for the development of high powered rockets suitable for launch. The system utilizes a large languag...
Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearned capabilities can re-emerge, ...
Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning ...