Category
9,261 papers
A Dual-evidence framework with adaptive Fusion and Aggregation (DiFA) for token-level anomaly detection, which derives anomaly scores from form-structural and semantic views to capture visible structural abnormality and contextual inconsistency, thereby providing complementary evidence for identifying diverse anomalies...
This work forms the pruning objective as a cardinality-constrained binary quadratic program that explicitly models cross-unit dependencies in the reconstruction error, and develops a greedy interaction algorithm based on dependency-aware marginal costs to optimize unit selection.
A dual-pathway intervention is proposed that combines prompt sanitization with activation counter-steering to suppress both external evaluation triggers and their internal representations and suggests that effective mitigation requires jointly addressing both prompt-level and representation-level signals.
Under a softmax retrieval abstraction, a finite-sample upper bound is derived showing that maintaining a fixed accuracy target above base rate requires the evidence margin to scale as $\Omega(\sqrt{\log N})$, where N denotes the effective distractor count rather than necessarily the raw context length.
Reach audiences
Advertise in front of researchers, engineers, and readers.
AdaMem is a relevance-guided soft-compression framework that maps learned passage-relevance estimates to a query-dependent allocation of a fixed memory-token budget and retains an efficiency profile comparable to the uniform-compression baseline, while achieving up to $4\times lower inference latency than full-context...
An interactive visual analytics system is developed to navigate the comparison landscape, identify pairs of interest, and drill down into discriminative tokens and their code contexts, as well as defining two new metrics: robustness and concentration.
Content moderation systems traditionally entangle multimodal understanding with policy-specific classification, requiring full pipeline retraining for every policy change and suffering from label scarcity since multimedia cannot be meaningfully augmented. We propose Summarize-Judge-Refine (SJR), a two-model architectur...
Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later interactions, their variation can reflect downstream randomness rather than differences between the current actions. We introduce Critical-State...
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
This work trains a plain incremental LoRA (IncLoRA) with Muon, which orthogonalizes each update, and compares it against O-LoRA and ELLA over five seeds and three task orders on the Standard CL Benchmark and three seeds on TRACE.
An information-efficiency ratio (IER) based on a signal-to-noise decomposition and a candidate-set approximation enables token selection based on IER and its combination with existing usefulness scores, while retaining the sampled reverse-KL training objective.
SupportCal is introduced, a label-free post-hoc method that retains agreement examples at unit weight and assigns disagreement examples continuous weights based on the own-base PLM's relative support and corroboration from pretrained references selected from a size-compatible candidate pool.
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
