Posters

Logistic Schedule: A novel noise schedule revolutionizes image editing by improving DDIM inversion, enhancing content preservation and edit fidelity without model retraining!

SceneDiffuser: a scene-level diffusion model revolutionizes driving simulation by uniting scene initialization and rollout, enabling efficient and controllable closed-loop traffic generation.

SceneCraft generates highly detailed indoor scenes from user-provided textual descriptions and spatial layouts, overcoming limitations of previous text-to-3D methods in scale and control.

SDSGG outperforms leading scene graph generation methods by using LLMs to create scene-specific descriptions, adapting to diverse visual relations.

SCaR refines skill chaining for long-horizon robotic manipulation via dual regularization, achieving higher success rates and robustness.

TRODO: a novel trojan detection method using out-of-distribution samples, effectively identifies trojaned classifiers even against adversarial attacks and with limited data.

CRATE-a: A new white-box vision transformer architecture achieves 85.1% ImageNet accuracy by strategically scaling model size and datasets, outperforming prior white-box models and preserving interpre…

Stormer, a simple transformer model, achieves state-of-the-art medium-range weather forecasting accuracy by using weather-specific embedding, randomized dynamics forecasting, and a pressure-weighted l…

VQGAN-LC massively scales VQGAN’s codebook to 100,000 entries while maintaining a 99% utilization rate, significantly boosting image generation and downstream task performance.

Researchers dramatically improved sign language translation by scaling up data, model size, and the number of languages, achieving state-of-the-art results.

Massive language models improve with bigger datastores at inference time. A 1.4 trillion-token datastore, MASSIVEDS, shows that retrieval-based LMs outperform larger, solely-trained models on knowled…

Boosting LLM performance: This research shows how larger language models need bigger vocabularies for optimal efficiency and performance.

Deep learning’s neural scaling laws defy conventional wisdom; this paper uses infinite-dimensional linear regression to theoretically explain this phenomenon, showing that implicit regularization of S…

Direct Alignment Algorithms (DAAs) for LLM alignment suffer from over-optimization, even without explicit reward models; this paper empirically demonstrates this and proposes scaling laws to understan…

Boost machine learning with surrogate data! A novel weighted ERM method effectively integrates surrogate data, significantly reducing test errors even with unrelated data, guided by a predictable sca…

Unlocking the potential of deep learning for time series forecasting: this study reveals a scaling law influenced by dataset size, model complexity, and the crucial look-back horizon, leading to impro…

ScaleKD: Pre-trained vision transformers make excellent teachers for diverse student networks, improving efficiency and performance in knowledge distillation.

Scale-invariant optimal subsampling tackles computational challenges in analyzing massive rare-events data with sparse models, enhancing parameter estimation and variable selection without being affec…

Deep learning optimization gets a major upgrade with Modula, a new method that uses the modular norm to normalize weight updates, enabling learning rate transfer across network widths and depths, thus…

BICCOS: Scalable neural network verification via branch-and-bound inferred cutting planes.