Toward a future that preserves benefits of neurotechnology for all
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
More from the blog
GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models
What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research.
Advancing AMIE towards expert-level audio-visual clinical consultations
Health & Bioscience
The benefits of medical AI assistance vary based on user expertise
Study finds non-experts deferred to LLM-based diagnostic assistance, even when it was wrong, while clinicians caught AI errors.
SymptomAI: Towards a conversational AI agent for everyday symptom assessment
General Science
Related papers
Constitutional Midtraining: Content Presence Drives Alignment Gains
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtraining at 120B scale, where principled, values-based content is inserted into midtraining. A 2x2 design (curriculum ordering x deliberative reasoning) was used to produce four constitutionally midtrained conditions, plus a control, which were evaluated on self-generated and established benchmarks including alignment under pressure, value conflict resolution, blackmail, and emergent misalignment. All models were evaluated across three stages: post-midtraining, post-SFT, and post-benign fine-tuning. Constitutionally midtrained models outperformed the control on alignment generalization and durability, notably on blackmail: SFT instilled a blackmail propensity in all models, but constitutional midtraining blunted it, with the advantage surviving benign fine-tuning (-17.5pp). This durability did not extend to settings that required active resistance to in-context pressure or conflict, where the advantage attenuates after SFT. The presence of constitutional content at midtraining also mattered more than its structure, and constitutional midtraining incurred no capability cost, on average, at any stage (MMLU, ARC-Easy, piqa, GSM8K). A modest amount of constitutional content at midtraining could therefore yield broad, persistent alignment gains, offering a cheap, complementary addition to SFT-centered pipelines. Code, data, and models are available.
PROTEUS: A 40 nm Programmable General-Purpose Digital Compute-In-Memory Accelerator With eNVM and Hierarchical ISA for Versatile Edge AI
We present PROTEUS, an 18 mm2 programmable general-purpose digital compute-in-memory (GP-DCIM) accelerator integrating 4 Mb resistive random access memory (RRAM) and 2.6 Mb tensor static random access memory (SRAM) with a 32-bit hierarchical DCIM instruction set architecture (ISA). PROTEUS features fine-grained 1-D matrix tiling and a reconfigurable DCIM datapath/pipeline for near-100% memory utilization, supporting INT8/INT16/FP8/FP16 DCIM computations. PROTEUS unifies SRAM/RRAM dataflows and embeds nonvolatile micro-programs in RRAM to enable rapid switching among prestored kernels without incurring off-chip instruction feeds or RRAM rewrites. Fabricated in 40 nm ultra-low power (ULP) CMOS with foundry RRAM, PROTEUS delivers 702 GOPS throughput, 6.4 TOPS/W energy efficiency, and 0.039 TOPS/mm2 compute density. It is validated on ResNet-20, BERT-Tiny, MobileViT, GraphSAGE, and Vision Mamba, demonstrating versatility across CNN, Transformer, hybrid CNN-Transformer, graph neural network (GNN), and state-space model (SSM) workloads.
Bernstein-Vazirani Networks: Quantum Machine Learning by Interference
We introduce Bernstein-Vazirani Networks (BVNs), a non-variational quantum machine learning framework that leverages quantum interference for supervised learning, demonstrated on vision and representation learning tasks. In their standard form, BVNs follow the principle of quantum Fourier sampling: labelled data are placed in superposition and interfered in the Fourier basis to extract globally informative features. We then define generalised BVNs that enable interference in problem-adapted bases, yielding more expressive models under the same measurement budget as in the standard setting. BVNs achieve universal function approximation through (over)complete interference bases, while training of BVNs is gradient-free. Experiments on synthetic and real-world classification tasks, as well as implicit image representation, show strong generalisation capabilities and competitive performance with classical and quantum baselines.
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket
This work introduces a pioneering exploration of Self-Supervised Learning (SSL) within the SNN, and proposes a novel Spiking Self-Attention (SSA) and Spiking Transformer (Spikformer) that achieves 80+% accuracy on ImageNet.