Search and filter through extracted claims from AI researchers.
Showing 2141-2160 of 4537 claims
Foundation models introduce transferable prior knowledge that offers new ways to address hand-object interaction modeling challenges beyond task-specific data and models
The literature on foundation models for hand-object interaction remains fragmented, with studies typically describing methods simply as 'using large models' without systematic characterization
Finetuned graph language model retrievers generalize better out of domain than GNN-based retrievers, achieving SOTA on two multi-hop benchmarks
Graph language models show promising scaling as parameters and subgraph coverage increase in retrieval-augmented generation tasks
Computer-use agents often fail on transient GUI events because expensive autoregressive decoding is on the decision-time critical path
Adaptive Anticipatory Policy Trees improve agent success rate from 0.50 to 0.79 within contested decision windows by pre-computing conditional policy trees during idle periods
Most segmentation algorithms lack the generalisation capacity required for large-scale flood monitoring application, while annotated flood data are scarce and unevenly distributed
Existing post-training quantization methods are poorly suited to World Action Models because they rely on open-loop objectives, homogeneous model assumptions, and calibration distributions that do not reflect deployment
QuantWAMs framework can align quantization decisions with calibration context for World Action Models through shared-basis outlier calibration, co-training-objective saliency, and fixed-intervention rollout auditing
PACE framework extends the use of LLMs in finance from what to trade to how to execute, requiring neither explicit market assumptions nor task-specific training
PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines by 0.65 bps on Shenzhen Stock Exchange Level-1 data
Windowed thinning achieves query complexity of O(κ^(1/2)d(d log κ + log 1/ε)) gradient queries for bouncy particle sampler and O(κd^(1/4)(d log κ + log 1/ε)) full-gradient equivalents for Zigzag
Static structured pruning methods for LLMs cause substantial accuracy degradation under aggressive sparsity due to input-agnostic computation allocation
Dynamic sparsity methods improve quality retention by adapting computation to individual inputs, but their practical acceleration under real-world inference scenarios remains challenging
WIDE is the first end-to-end differentiable token-level dynamic width pruning framework designed for both prefill and decode scenarios
Token-level dynamic width pruning enables fine-grained computation allocation by allowing each token to dynamically select attention-head groups and FFN-channel groups at neuron-block-level granularity
LLMs exhibit derived-feature over-trust (DFOT), a failure mode where they assign derived measurements the epistemic status of direct facts or use them outside their valid scope
LLMs fail to properly assess the instance-dependent validity of derived measurements in medical contexts, accepting contradicted measurements and rejecting reliable ones under misleading context
Frontier LLMs can achieve strong performance in social deduction scenarios requiring deception, persuasion, and reasoning under information asymmetry
GPT-5.4, Kimi K2.5, Grok 4.1 Fast, and DeepSeek 3.1 Terminus form a strong top-four cluster in social deduction capabilities
Pipeline data may be stale or degraded.
Last synthesis: 2026-09-20. 9,033 pending.