Vision-language models (VLMs) are deployed as zero-shot judges of image aesthetics, and panels of several models are recommended, on thin evidence, as the way to make such judges reliable. On two human-rated datasets, EVA and PARA, we find that a panel of holistic judges never significantly beats its best member, wheth...
Amit Jadhav, Shaurya Beriwala, Beomjin Kim· 0 citations
Large language models have enabled rapid deployment of language classification and analysis, allowing users to describe complex constructs in natural language, such as pedagogical moves or expressions of learning and engagement, and label them in conversational datasets such as classroom or tutoring transcripts. Howeve...
Julian Bernado, Ana T. Ribeiro, Xander Beberman et al.· 0 citations
LexLattice is introduced, an extractive summarizer that reifies a legal act's hierarchy as a two-dimensional semantic lattice and consolidates over it with a masked 2D neural cellular automata before selection and position explicit consolidation over document structure as a compact and traceable alternative to scale fo...
This work shows that LLMs can be used to strategically target expert attention, shortening months of codebook revision to days without sacrificing labeling performance.
Ze-Yu He, Zhu-Qian Zhou, Kirk P. Vanacore et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces MemeCF, a cue-focused benchmark of 9,895 memes across harm, hate, and sarcasm, with annotations identifying the modality and rationale of the pivotal evidence.
Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a model's internal representations stay invariant too? We investigate this question using synthetic multi-step function-composition problems, each presented under multiple rule orderings with the same correc...
This work extends balanced-tree recursive operators from sequence encoding to autoregressive prediction, enabling all prefix representations to be computed with logarithmic depth and linear runtime.
Yi-Qing Wang, Nuri Cingillioglu, C. Pert· 0 citations
Mixture-of-Experts (MoE) training requires global load balance to prevent expert under-utilization and local balance for efficient expert-parallel execution. Existing distributed Quantile Balancing (QB) uses shard-dependent or approximate global quantiles, while token-independent expert biases cannot ensure microbatch-...
Pit Neitemeier, Jiaze Li, Alessio Serra et al.· 0 citations
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it pro...
Direct transfer of Step Law systematically overestimates the optimal learning rate: the median ratio eta_SL / eta* is approximately 4.0x, with a range of 2.4x to 6.6x.
Egor Romanyukov, Timofey Novikov, Timur Shokarov et al.· 0 citations
Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields...
It is argued that the Linear Representation Hypothesis is not one hypothesis but a family of claims distinguished by representation equivalence, and this framework clarifies how assumptions can change across metrics, reading points, and analysis stages, and is used to audit common representation quantities and recent i...
Louie Hong Yao, Yu-Hao Li, Sheng-Chao Liu· 0 citations
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.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
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.
