MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Attribution graphs over the features of sparse autoencoders (SAEs) are used to predict what an ablation does and are compared across training seeds. A TopK SAE keeps the largest preactivations at…
Conversational text-to-SQL interfaces could give healthcare professionals natural-language access to electronic health record (EHR) data, but evidence for their real-world usability remains limited:…
Sparse autoencoders (SAEs) have recovered interpretable, causally relevant features in robot foundation models (RFMs) such as $π_{0.5}$ (arXiv:2603.19183, arXiv:2603.19233). SAE features on…
Does eliciting five weighted estimates within a single response change how a language model responds to information? Across anchoring, hindsight, base-rate, conjunction, and status-quo/default tasks,…
Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during…
A growing body of work reports benefits from orthogonality constraints in fine-tuning large language models (LLMs). These results raise an open question: do orthogonality constraints also help LLM…
Finding the passage that answers a question is the first step of most practical systems built on documents, and for Tajik we found no openly described model for it. We present…
Activation recomputation saves accelerator memory by replaying forward segments during the backward pass, but replay is only correct if it sees the state the original forward pass saw. Mutable…
Adam keeps two FP32 moments per parameter, twice the bytes of the FP32 weights, yet compressing them is risky: the update divides by the square root of the second moment, so small reconstruction…
Speculative decoding accelerates LLM inference with a drafter whose proposed tokens are verified by the target model in parallel. Under lossless speculative sampling, a draft token is accepted with…
Recently, reinforcement learning from verifiable rewards (RLVR) is practically very important, where the leading approach is group relative policy optimization (GRPO) that typically faces a trade-off…
Attention is the computational core of large language models, yet the verifiers that bound how far an attention head's output can move under input perturbations give no guarantee on how loose their…
Voluntary platoon formation requires vehicles to coordinate despite uncertain downstream fuel savings and private joining incentives. We study whether an informed operator can encourage participation…
Accurate posture feedback is essential for precise control of continuum robots. Off-the-shelf bend sensors measure curvature about only one axis; without a suitable mounting arrangement, they can…
Scientific discovery advances when evidence from different investigations is brought into contact. Yet paper-centric communication leaves experimental results fragmented, delayed, or unreported,…
Test-time search can improve structured planning, but when methods differ in prompts, post-processing, and selection, it is unclear what an observed gain should be attributed to. We study this…
A deployed model sees its inputs for free, but checking whether its risk has risen requires costly labels. We study how to spend a label budget so that a risk increase is detected quickly while false…
Structured channel pruning for convolutional neural networks (CNNs) plays an important role in pattern recognition and deep learning. Nevertheless, existing methods usually calculate channel…
Web API recommenders return a set of APIs for a mashup request but do not check it against provider documentation, the main public evidence of an API's capabilities. The set can therefore contain…
Tabular foundation models (TFMs) enable in-context prediction on unseen tabular datasets without task-specific training. Mechanistic work has shown that increasing the depth of the ICL Transformer…
Recent work has demonstrated agents driving protein design workflows, either through orchestration of specialized tools or direct manipulation of sequences. Yet the fidelity with which agents follow…
Large gaps in seismic acquisition disrupt reflection events and hinder spectral recovery. Existing seismic interpolation deep unfolding networks primarily rely on localized spatial priors, limiting…
Does the level of test-time processing effort affect a language model's computational capability? A formal grammar-lens benchmark method, derived from the theory of computation, generates novel data…
Reasoning-oriented post-training enables large language models (LLMs) to solve complex tasks via multi-step inference. Supervised fine-tuning (SFT) on high-quality reasoning traces is a particularly…