AdaFocus achieves better accuracy on long-video benchmarks with roughly 33 times fewer visual tokens by combining query-aware adaptive sampling and zero-cache disk-based refinement.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
ComeIR introduces dual-level Engram memory and memory-restoring prediction to reconstruct SID-token embeddings and restore token granularity in generative recommendation.
TIGS detects backdoor-induced attention collapse in LLMs and applies content-aware tail-risk screening plus intrinsic geometric smoothing to suppress attacks while preserving normal performance.
The paper measures policy-carriage failures during LLM context assembly and evaluates SafeContext as a partial mitigation on Llama, Qwen, and Mistral models.
MLA-Gen advances text-driven motion synthesis by aligning global motion patterns with fine-grained text semantics and mitigating attention sink effects via new masking techniques.
PiKV proposes expert-sharded KV storage, PiKV routing, adaptive scheduling, and compression modules to reduce overhead in multi-GPU MoE inference.
citing papers explorer
-
AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding
AdaFocus achieves better accuracy on long-video benchmarks with roughly 33 times fewer visual tokens by combining query-aware adaptive sampling and zero-cache disk-based refinement.
-
Conditional Memory Enhanced Item Representation for Generative Recommendation
ComeIR introduces dual-level Engram memory and memory-restoring prediction to reconstruct SID-token embeddings and restore token granularity in generative recommendation.
-
Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing
TIGS detects backdoor-induced attention collapse in LLMs and applies content-aware tail-risk screening plus intrinsic geometric smoothing to suppress attacks while preserving normal performance.
-
Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly
The paper measures policy-carriage failures during LLM context assembly and evaluates SafeContext as a partial mitigation on Llama, Qwen, and Mistral models.
-
Exploring Motion-Language Alignment for Text-driven Motion Generation
MLA-Gen advances text-driven motion synthesis by aligning global motion patterns with fine-grained text semantics and mitigating attention sink effects via new masking techniques.
-
PiKV: KV Cache Management System for Mixture of Experts
PiKV proposes expert-sharded KV storage, PiKV routing, adaptive scheduling, and compression modules to reduce overhead in multi-GPU MoE inference.