Posters

CALVIN: Instruction tuning boosts contextual video captioning, achieving state-of-the-art results!

LLMs’ reasoning can be improved by using internal consistency to calibrate their outputs.

Calibrated Self-Rewarding (CSR) significantly improves vision-language models by using a novel iterative approach that incorporates visual constraints into the self-rewarding process, reducing halluci…

CALANet: Cheap All-Layer Aggregation boosts real-time HAR accuracy by efficiently aggregating features from all layers, achieving state-of-the-art performance on seven benchmark datasets.

Cal-DPO calibrates implicit rewards in contrastive preference learning, dramatically improving large language model alignment with human preferences.

CA-SSLR: a novel self-supervised learning model dynamically adapts to various speech tasks by integrating language and speaker embeddings, improving performance and reducing reliance on audio features…

C-GAIL stabilizes Generative Adversarial Imitation Learning by applying control theory, resulting in faster convergence, reduced oscillation, and better expert policy matching.

Byzantine-tolerant Variance-Reduced MARINA with Partial Participation (Byz-VR-MARINA-PP) is the first distributed method to simultaneously achieve Byzantine robustness and partial client participation…

Training large language models efficiently is key; this paper shows how using structured feedforward layers and a novel training regime significantly reduces computational costs and improves training …

Boost classifier stability with the novel inflated argmax, guaranteeing reliable multiclass classification without distributional assumptions!

InLine attention, a novel method, bridges the performance gap between softmax and linear attention by incorporating injectivity and local modeling, achieving superior performance while maintaining lin…

AI agents learn human-like communication, combining semantic categorization and pragmatic context-sensitive reasoning, through a novel information-theoretic framework.

A novel graph-theoretic framework bridges OOD detection & generalization, offering theoretical error bounds and competitive empirical performance.

New model-agnostic framework for out-of-distribution generalization uses multicalibration across overlapping groups, showing improved robustness and prediction under various distribution shifts.

BRAID: A novel, conservative fine-tuning method surpasses offline design optimization by cleverly combining generative diffusion models with reward models, preventing over-optimization and generating …

Geometric Diffusion Bridge (GDB) accurately predicts geometric state evolution in complex systems by leveraging a probabilistic approach and equivariant diffusion processes, surpassing existing deep l…

FMCSC: A novel federated multi-view clustering framework bridging client and view gaps in heterogeneous hybrid views, achieving superior performance through local-synergistic contrastive learning and …

Bridge-IF, a novel generative diffusion model, excels at inverse protein folding by learning probabilistic dependencies between protein structures and sequences, significantly outperforming existing m…

SWAB bridges modality and capability gaps in Vision-Language Model selection using optimal transport, enabling accurate prediction of VLM performance without images.

Researchers discover that existing backdoor defenses leave vulnerabilities, allowing for easy re-activation of backdoors through subtle trigger manipulation.