Search posts, papers, and topics
Alibaba's Damo Academy open-sourced Damo Radar, an AI model that detects nearly 150 abdominal conditions, including cancers, from CT scans. It achieved an average AUC of 0.913 across 146 clinical findings and outperformed most human radiologists in a comparative study.
ActObs is a supervised fine-tuning method that trains agents to predict both actions and environmental observations from trajectories. This joint supervision improves subsequent reinforcement learning performance, leading to better exploration and task completion on benchmarks like Terminal-Bench 2.0 and aider-polyglot.
PPO critics in reinforcement learning for LLMs suffer from "Value Flattening," where predicted state values are too flat compared to actual values. This paper identifies the causes as an implicit variance penalty and redundant updates, and proposes SParse Proximal Policy Optimization (SP3O) to mitigate it by supervising only a few well-separated states.
This paper introduces SpectralShift, a spectral reparameterization method for extending the context window of Gated DeltaNet (GDN) linear attention models. It reconfigures the decay spectrum by enhancing slow propagation and preserving fast-decaying modes, consistently improving long-context capabilities during continual pretraining.
This paper investigates the "lossless" claim of Orthrus, a hybrid architecture for accelerating LLM inference. It finds that under BF16 precision, Orthrus diverges from the exact autoregressive output trajectory in over 50% of cases, though FP32 maintains exact matching. Despite BF16 divergence, downstream task performance was not systematically degraded.
ModAR is a world‑action model that autoregressively denoises multiple future modalities (depth, DINO features, point tracks) before predicting actions, letting each prediction condition on earlier outputs. It outperforms prior WAMs, achieving higher success rates with ~20× fewer training FLOPs and no pretraining.
This paper introduces a training-adaptive Convolutional Sparse Coding (CSC) framework where the sparsity coefficient is learned end-to-end via FISTA unfolding. It uses an information bottleneck perspective to balance representation compression and content preservation, showing improved robustness to input perturbations on CIFAR and ImageNet.
Paper evaluates a standard 3‑D nnU‑Net on the new BraTS‑GoAT benchmark, training on 1,351 cases with five‑fold cross‑validation and test‑time mirroring. It reports Dice scores of 0.78/0.83/0.89 (ET/TC/WT) and shows a ~0.07 drop on heterogeneous validation, with limited benefit from ensembling or mirroring and failure linked to small, fragmented tumors.
