Amir

CLANE presents an end-to-end continual action recognition system deployed on neuromorphic hardware (Intel Loihi 2) using event cameras, achieving high accuracy with massive reductions in energy and latency compared to traditional methods.

AI-PROPELLER introduces a novel interprocedural code layout optimization system that uses an agentic evolutionary workflow to achieve significant, measurable performance gains in large-scale, real-world binaries.

The paper proposes GC-MoE, a graph-conditioned Mixture of Experts framework, to improve traffic forecasting by assigning personalized, specialized forecasting experts to individual road segments.

iLoRA introduces a novel Bayesian graph-conditioned LoRA framework that jointly learns prediction and latent interaction structure, significantly improving microbiome diagnosis by modeling microbe-microbe cross-talk.

The paper proposes replacing expensive, always-on LLM calls for proactive agent triggering with a specialized Temporal-Graph-Learning (TGL) model, significantly improving efficiency and performance.

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring specialized training or supervision.

The paper demonstrates that using English prompts causes large language models to prioritize globally dominant narratives over local cultural knowledge, even when local evidence is provided.

The paper introduces the Terminal Representation (TR), a novel, lower-dimensional, and structurally distinct formulation for encoding reward-weighted trajectories in RL that bypasses the need for eigendecomposition while retaining the benefits of existing representations.

The paper introduces a novel padding method that leverages crystal symmetry to enhance the encoding of complex inorganic structures, significantly improving the generation of stable, novel materials.

The paper designed a minimalist BCMI system to translate EEG-measured emotional valence into adaptive music, but preliminary testing showed that frontal alpha asymmetry was not reliably modulated by intentional emotional states.

The paper introduces TukaBench, a culturally grounded jailbreak benchmark for seven African languages, demonstrating that prompting in African languages, especially with cultural adaptation, significantly reduces LLM refusal rates compared to English.

The paper introduces STARFISH, a novel healing method that efficiently recovers significant accuracy in heavily pruned neural networks by optimizing the pruned model to match the original network's internal state representations.

The paper establishes a benchmark based on the cheap-talk model to test LLM honesty when their incentives conflict with the user's, finding that models consistently over-reveal information regardless of the bias level.

The paper proposes a dual-encoder architecture that fuses processed acoustic waveforms and spectrograms using a differentiable Choquet integral to improve underwater acoustic classification while maintaining parameter efficiency.

The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is significantly harder in low-resource languages and that literal interpretations pose a greater challenge than figurative ones.

The paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework that enables stable, scalable consensus control for large swarms of quadcopters using only local neighbor information.

The paper introduces TalkTag, an LLM-based tool that automates fine-grained morphosyntactic error annotation for spoken-language transcripts, providing a scalable alternative to labor-intensive manual annotation.

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

The paper proposes Shallow-RHS, an asymmetric graph-completion model, to solve the cold-start problem for both new content and new devices in large-scale recommendation systems.

This paper enhances open-source FPGA CAD tools to model and explore inter-die routing architectures for 2.5D and 3D FPGAs, demonstrating that these architectures can significantly improve performance and capacity.