Posters

ROBIN: A novel watermarking method for diffusion models that actively conceals robust watermarks using adversarial optimization, enabling strong, imperceptible, and verifiable image authentication.

Garner, a novel framework, enhances road network representation learning by incorporating the Third Law of Geography, significantly boosting performance in downstream tasks.

RMLR: A novel framework extends multinomial logistic regression to diverse geometries, overcoming limitations of existing methods by requiring minimal geometric properties for broad applicability.

RLE: A novel data augmentation strategy unifying cross-spectral re-ID, significantly boosting model performance by mimicking local linear transformations.

Leveraging model-generated synthetic data for LLM finetuning significantly improves efficiency when using both positive and strategically constructed negative examples, resulting in an eight-fold incr…

First sample-efficient algorithm for LMDPs without separation assumptions, achieving near-optimal guarantees via novel off-policy evaluation.

Risk-sensitive control is recast as inference using Rényi divergence, yielding new algorithms and revealing equivalences between seemingly disparate methods.

Risk-Averse RLHF fine-tunes LLMs to minimize toxic outputs while maintaining performance.

VLMs struggle with insufficient visual info for Q&A; this work introduces a novel Directional Guidance task and a data augmentation framework, significantly improving VLM performance by teaching them …

Richelieu: a self-evolving LLM-based AI agent masters Diplomacy, a complex game requiring strategic planning and negotiation, without human data, by integrating self-play for continuous improvement.

RGMDT algorithm extracts high-performing, interpretable decision trees from deep RL policies, guaranteeing near-optimal returns with size constraints, and extending to multi-agent settings.

Reaction-GFlowNet (RGFN) revolutionizes small molecule discovery by generating synthesizable molecules directly within the chemical reaction space, dramatically expanding the search space for drug dis…

RFLPA: Secure Federated Learning resists poisoning attacks via efficient secure aggregation.

Deep RL agents can now effectively learn complex tasks even with noisy, uncertain sensor readings by exploiting the structure of Reward Machines.

Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation dynamically adjusts class weights during training using density ratio estimation, significantly improving model generalization, e…

GLMix: A novel vision backbone efficiently integrates convolutions and multi-head self-attention at different granularities, achieving state-of-the-art performance while addressing scalability issues.

SCHOOL: A novel SHGL framework enhancing spectral clustering with rank and dual consistency constraints, effectively mitigating noise and leveraging cluster-level information for improved downstream t…

GRASP: A novel graph augmentation strategy boosts OOD node detection by strategically adding edges to enhance the intra-edge ratio, addressing score propagation’s limitations in various scenarios.

RGB-Event tracker CSAM leverages MOT philosophy for enhanced robustness by integrating appearance and motion information from RGB and event streams, achieving state-of-the-art performance.

FENS: a novel federated ensembling scheme that boosts one-shot federated learning accuracy to near iterative FL levels, while maintaining low communication costs.