Claims Browser

Timestamp-sorted CSR storage with binary search reduces per-node temporal sampling cost from O(deg(v) + k) to O(log(deg(v)) + k)

"We implement timestamp-sorted CSR storage with binary search, reducing the per-node temporal sampling cost from $O(deg(v) + k)$ to $O(\log(deg(v)) + k)$."

A scalable GNN ranking system increased friend additions from recommendations by 16 percent and unique friend adders by 11.5 percent in production

"In an online A/B test, our system increases friend additions from recommendations by 16 percent and unique friend adders by 11.5 percent over a strong production baseline."

Message-passing GNNs can be successfully deployed on production-scale social graphs with hundreds of millions of users and tens of billions of edges

"We present a scalable end-to-end GNN ranking system for production social graphs, focusing on two design choices that are critical in this setting: multi-hash ID embeddings and temporal neighbor sampling."

Vision-language models contain Visual Retrieval Heads (VRHs), a small subset of about 1.7-2.6% of attention heads that are causally responsible for grounding text descriptions to image regions

"Visual Retrieval Heads (VRHs), a small subset of attention heads (about 1.7-2.6%) that are causally responsible for grounding text descriptions to image regions"

Masking only the top 20 VRHs reduces grounding accuracy by up to 80 percentage points across eleven VLMs and five benchmarks, demonstrating their causal importance

"Across eleven VLMs and five referring-expression benchmarks, masking only the top 20 VRHs reduces grounding accuracy by up to 80 percentage points, while masking the same number of random heads has little effect"

Visual Retrieval Heads generalize across visual reference tasks, remaining causal on attribute, spatial, counting, and visual-math benchmarks despite being discovered through bounding-box prediction

"they generalize across visual reference tasks, remaining causal on attribute, spatial, counting, and visual-math benchmarks despite being discovered through bounding-box prediction"

VRHs are functionally specific, preserving output format while corrupting localization

"they are functionally specific, preserving output format while corrupting localization"

VRHs are architecturally shared, transferring causally across VLMs that share an LLM backbone but differ in vision encoder, projector, and instruction tuning

"they are architecturally shared, transferring causally across VLMs that share an LLM backbone but differ in vision encoder, projector, and instruction tuning"

Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves LLM reasoning but often causes a drop in policy entropy, leading to narrowed reasoning coverage and degraded pass@k for large k

"Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves LLM reasoning but often causes a drop in policy entropy, leading to narrowed reasoning coverage and degraded pass@$k$ for large $k$."

Current MLLM agents show useful atomic abilities in visual recognition and short-range spatial reasoning

"Contemporary MLLM agents usually show useful atomic abilities in visual recognition and short-range spatial reasoning"

Forcing the target model to generate answers based on partial reasoning trajectories from smaller, weaker language models effectively disrupts over-confidence and encourages exploration of distinct reasoning paths

"Instead of relying solely on internal exploration, we force the target model to generate answers based on partial reasoning trajectories generated by a smaller, weaker language models. These unfamiliar prefixes effectively disrupt over-confidence and encourage the exploration of distinct reasoning paths."

The proposed method consistently outperforms vanilla RLVR across multiple mathematical benchmarks, with performance gains becoming more pronounced as k scales up

"Experiments across multiple mathematical benchmarks show that our method consistently outperforms vanilla RLVR. Notably, the performance gain becomes increasingly pronounced as $k$ scales up, demonstrating a substantial expansion of reasoning coverage."

The approach efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting

"Furthermore, our approach efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting."

No learned alternative sepsis index derived directly from patient trajectories is currently in routine clinical use

"No alternative learned directly from patient trajectories is in routine use."

A new sepsis index using mortality as a treatment-level ranking signal rather than per-state target allows credit redistribution non-uniformly across timesteps, improving on previous approaches

"Unlike previous studies, we use mortality as a treatment-level ranking signal rather than a per-state target, allowing credit to be redistributed non-uniformly across timesteps."

The new sepsis index separates non-survivors from survivors by 1.19-1.64 points on a 0-10 scale across all baseline SOFA-2 strata

"Under this ranking scheme, non-survivors scored 1.19-1.64 points higher than survivors on a 0-10 scale within all strata of baseline SOFA-2, with similar results stratifying within lactate, mean arterial pressure (MAP), and creatinine."

Cross-institutional agreement for the sepsis index models trained on different sites achieved 70-77% of same-site correlation, demonstrating reasonable generalization

"On a cohort level, cross-institutional agreement measured by Spearman correlation between models trained on different sites, were 70-77% of same-site correlation."

ModelAudit produced definitive security decisions for all 135 labeled artifact families, achieving 100% coverage

"ModelAudit produced definitive security decisions for all 135 families (100%)"