Latest AI/ML research from ArXiv and Papers with Code
Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitigation met...
As language-model agents grow more capable, they can carry more of a task without asking anyone for help. Falling reliance on a human partner is easy to read as a failure of collab...
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and e...
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files that the agen...
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A ...
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible t...
Diffusion-based video matting has recently emerged as a leading approach, leveraging video diffusion priors from internet-scale pretraining to achieve strong zero-shot generalizati...
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated. Unlike static...
We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on the adversarial split, sat 1.21 to 8.67 p...
Modern language models are increasingly asked to handle several tasks within a single prompt. Doing so requires solving each task correctly while integrating the resulting answers ...
Scene-level 3D generation has long been dominated by 2D multi-view or video diffusion models. Typically, these 2D-based approaches perform scene generation in a 2D latent space, wh...
Matryoshka Representation Learning (MRL) is designed to support flexible representation sizes by jointly optimizing nested prefixes. While effective, this design lacks an explicit ...
Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for strong T2I ge...
Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states. However, e...
Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed ...
We propose EMBER, a structure-based framework for TCR--pMHC binding prediction that eliminates the need for a predicted docked complex, and with it the placement error that dominat...
General-purpose manipulation requires reliable behavior across embodiments, objects, and task demands. We introduce HandsOn, a composable simulation platform and benchmark for cros...
Accurate inpatient risk prediction requires modeling heterogeneous clinical evidence that accumulates irregularly over time. This challenge spans in-hospital mortality, prolonged l...
Robotic manipulation is not merely observation-to-action generation, but the realization of task-specified state changes in the physical world. Existing vision-language-action (VLA...
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we intro...
Game world models have made rapid progress toward real-time interactive generation. Yet action control is still predominantly implemented as feature conditioning, leaving the model...
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify phys...
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each question and redo...
Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often holds at the aggregate level, we p...