Posters

MambaAD: Linear-complexity multi-class unsupervised anomaly detection using a novel Mamba-based decoder with Locality-Enhanced State Space modules.

MALT: a novel adversarial attack, is 5x faster than AutoAttack, achieving higher success rates on CIFAR-100 and ImageNet by exploiting mesoscopic almost linearity in neural networks.

CoWorld: a novel model-based RL approach tackles offline visual RL challenges by using online simulators as testbeds, enabling flexible value estimation & mitigating overestimation bias for effective …

Make-it-Real uses a large multimodal language model to automatically paint realistic materials onto 3D objects, drastically improving realism and saving developers time.

Make-An-Agent generates high-performing robotic control policies from single behavioral demonstrations using behavior-prompted diffusion, showcasing impressive generalization and real-world applicabil…

FILM-7B, trained with Information-Intensive (IN2) training, significantly overcomes the ’lost-in-the-middle’ problem in long-context LLMs, enabling robust information retrieval from all context positi…

Boost continual learning with C-Flat: a novel, one-line-code optimizer creating flatter loss landscapes for enhanced stability and generalization across various continual learning scenarios.

Maia-2: A unified model for human-AI alignment in chess, coherently captures human play across skill levels, significantly improving AI-human alignment and paving the way for AI-guided teaching.

MagR: a novel preprocessing technique boosts post-training quantization of LLMs by reducing weight magnitudes without inference overhead, achieving state-of-the-art performance.

Magnet: Enhancing Text-to-Image Synthesis by Disentangling Attributes in CLIP.

MAGNET, a novel adaptive gradient-based tokenization method, tackles multilingual language model bias by employing language-specific boundary predictors to achieve equitable segmentation across divers…

MAGIS: A novel LLM-based multi-agent framework significantly boosts GitHub issue resolution by leveraging agent collaboration for planning and coding, achieving an eight-fold performance increase comp…

MADIFF: Offline multi-agent learning uses attention-based diffusion models to achieve effective coordination and teammate modeling, outperforming existing methods.

Multi-Agent System for Condition Mining (MACM) dramatically boosts large language model accuracy in complex math problem-solving, exceeding existing methods by achieving higher accuracy and better gen…

Improved facility location mechanisms are designed using ‘Mostly Approximately Correct’ predictions, exceeding prior bounds despite large prediction errors.

M³GPT, a novel multimodal framework, achieves superior motion comprehension and generation by integrating text, music, and motion data into a unified LLM representation.

LuSh-NeRF: A novel model reconstructs sharp, bright NeRFs from hand-held low-light photos by sequentially modeling and removing noise and blur, outperforming existing methods.

Lumina-Next supercharges image generation: faster, more efficient, and better resolution with new architecture and sampling techniques.

Lumen: A novel LMM architecture decouples perception learning into task-agnostic and task-specific stages, enabling versatile vision-centric capabilities and surpassing existing LMM-based approaches.

LT-Defense: a searching-free backdoor defense for language models leveraging the long-tailed effect of poisoned data. It achieves 98% accuracy across 1440 models with less than 1% time cost of existin…