Candidate Selection
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Voters select candidates in key House districts that could decide the majority
The ballots are set in two Republican-held battleground House races in Iowa, part of a slate of primaries Tuesday shaping the battle for control of Congress in the fall. As far as the primaries were concerned, there wasn’t much suspense in the two districts expected to be most competitive in the fall. Democratic former state Rep. Christina Bohannan will face off against GOP Rep. Mariannette Miller-Meeks for the third consecutive election in the southeastern part of the state, NBC News...
Reform knew of Makerfield candidate’s deleted accounts before selecting him
Reform UK has confirmed that it was aware of the controversial deleted social media accounts belonging to its Makerfield by-election candidate, Robert Kenyon, before selecting him. Kenyon disclosed these accounts during the vetting process, despite the posts containing remarks condemned as misogynistic and interactions with far-right figures. Labour has used this information to question the thoroughness of Reform's candidate vetting system.
Generalizing Fair Top-$k$ Selection: An Integrative Approach
arXiv:2603.04689v3 Announce Type: replace Abstract: Fair top-$k$ selection, which ensures appropriate proportional representation of members from minority or historically disadvantaged groups among the top-$k$ selected candidates, has drawn significant attention. We study the problem of finding a fair (linear) scoring function with multiple protected groups while also minimizing the disparity from a reference scoring function. This generalizes the prior setup, which was restricted to the...
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
arXiv:2602.07721v3 Announce Type: replace Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling...
Learning-Based Navigation for Indoor Mobile Robots
arXiv:2605.30468v1 Announce Type: new Abstract: This paper presents a learning-based navigation framework for indoor mobile robots. The proposed method combines a supervised neural global planner, trained from cost-aware A* expert trajectories, with the proposed Learning-Based DWA local planner, which is formulated as discrete candidate selection over the Dynamic Window Approach (DWA) action lattice. For local planning, the policy is first trained by behavior cloning and then refined by...
Reducing the Filtering Effect in Public School Admissions: A Bias-aware Analysis for Targeted Interventions
arXiv:2004.10846v5 Announce Type: replace Abstract: Problem definition: Traditionally, New York City's top 8 public schools have selected candidates solely based on their scores in the Specialized High School Admissions Test (SHSAT). These scores are known to be impacted by socioeconomic status of students and test preparation received in middle schools, leading to a massive filtering effect in the education pipeline. The classical mechanisms for assigning students to schools do not...
PInVerify: An Offline Embodied Benchmark for Active Instance Verification
arXiv:2605.30639v1 Announce Type: new Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs. "white striped") often require close-range, multi-view inspection. We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide...
SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
Announce Type: replace Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions (ReLU, Sigmoid,...
Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
Announce Type: new Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together. Fast-dLLM addressed this with KV caching and confidence-guided parallel decoding, but its decoding theory uses a homogeneous high-confidence assumption that effectively reduces each candidate set to its weakest selected token. We argue that this leaves speed on the table because real decoding steps...
Evaluation of Automatic Speech Recognition Using Generative Large Language Models
arXiv:2604.21928v3 Announce Type: replace Abstract: Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selecting the best hypothesis between two candidates, (2) computing semantic...