Claims Browser

Symmetrization of directed graphs can remove predictive information that is carried solely by edge direction

"controlled experiments show that symmetrization can remove predictive information carried solely by edge direction."

Llama-3.2-1B shows better TwinKV improvements on RULER benchmark than Qwen3-4B across all evaluated configurations

"On RULER with Llama-3.2-1B, however, that fourth policy improves in every evaluated cell because its Alone score leaves substantial room to improve."

Existing video-editing methods introduce facial-expression inconsistencies when applied to human-centric live streaming and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction

"directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction"

EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference

"Extensive experiments demonstrate that EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference"

A pretrained image animation model that naturally decouples appearance from motion can be repurposed as a base model for instruction-based human-centric video editing

"we start from a pretrained image animation model (Wan-Animate), which naturally decouples appearance from motion, and repurpose it as the base model for instruction-based human-centric video editing by reference frame editing and video reconstruction via the collected CharEdit-50K dataset"

An aligned self-rollout distillation strategy can compress a video editing model into a two-step sampler while reducing training-inference discrepancies and mitigating appearance drift

"design an aligned self-rollout distillation strategy that compresses the model into a two-step sampler, where fixed RoPE and align forcing reduce training--inference discrepancies, and first-frame preserved sparse attention filters redundant historical information to mitigate appearance drift"

Modern deep learning-based CSI predictors often provide only point predictions and lack calibrated uncertainty estimates

"Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates."

TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections

"Empirically, TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections, while avoiding the trajectory undercoverage of compact stepwise and adaptive conformal baselines."

TRACE-CRC avoids the trajectory undercoverage problems of compact stepwise and adaptive conformal baselines

"TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections, while avoiding the trajectory undercoverage of compact stepwise and adaptive conformal baselines."

Cross-cultural meme transcreation has three core challenges: culture-specific knowledge understanding, intent and tone preservation, and multimodal consistency

"we first provide an explicit task analysis of cross-cultural meme transcreation and identify three core challenges: culture-specific knowledge understanding, intent and tone preservation, and multimodal consistency"

A multi-agent framework with specialized agents can effectively address cross-cultural meme transcreation challenges through cultural adaptation, target text rewriting, revision, and conditional visual adjustment

"we propose a multi-agent framework with specialized agents that are coordinated to address these challenges through cultural adaptation, target text rewriting, revision, and conditional visual adjustment"

The proposed meme transcreation method achieves 33.1% average improvement over the strongest baseline in human evaluation and 60% Top-1 ranking rate versus 26% for the second-best baseline in LLM-as-a-Judge evaluation

"In human evaluation, it achieves the best performance on all four dimensions and delivers a 33.1% average improvement over the strongest baseline, while in LLM-as-a-Judge, it attains the highest Top-1 ranking rate (60% versus 26% for the second-best baseline)"

Attention magnitude is unrelated to a token's causal contribution to the answer in KV cache eviction

"Using a controlled leave-one-out probe, we find that attention magnitude is unrelated to a token's causal contribution to the answer (Spearman $ρ=-0.004$), challenging the premise behind dominant eviction methods."

TwinKV improves performance for a majority of configurations on two KV cache eviction policies when tested on Qwen3-4B

"On Qwen3-4B, TwinKV improves a majority of configurations for two policies, is near-even for a third, and helps only a minority for a fourth adaptive baseline already near a performance ceiling"

Long-context inference is bottlenecked by KV cache memory footprint, especially for small models

"Long-context inference is bottlenecked by the memory footprint of the key-value (KV) cache, especially for small models under tight resource budgets."

Multimodal foundation models show substantial inconsistencies when handling semantically equivalent queries across different modalities (text vs. speech) and languages (English vs. Arabic)

"it remains unclear whether semantically equivalent queries yield consistent judgments across modality (text vs. speech) and language (English vs. Arabic)"

Modality and language shifts introduce substantial triplet-level inconsistencies in multimodal models that are not fully captured by aggregate accuracy metrics

"modality and language shifts introduce substantial triplet-level inconsistencies that are not fully captured by aggregate accuracy"

Speech input amplifies partial failures in multimodal models compared to text input

"speech amplifying partial failures"

Current agent safeguards defined over single trajectories have a fundamental composition failure: against attacks fragmented across iterations, every trajectory-scoped monitor has equal true-positive and false-positive rates regardless of expressiveness.

"against an attack whose evidence is fragmented across several iterations, every trajectory-scoped monitor has a true-positive rate equal to its false-positive rate, however expressive it is, because the evidence it would need never appears in the window it sees"