Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the teacher-student capability mismatch is large. We revisit the capacity gap from a practical perspective by re-examining commonly used experim...
T. Kajitsuka, Ukyo Honda, Sho Takase· arXiv.org· 2 citations
Screening is introduced, whose explicit threshold transforms bounded query--key similarities into relevance values, enabling exact rejection, empty selection, and direct inspection on a common scale, in a controlled comparison of 12 attention mechanisms on a matched Transformer backbone.
Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central qu...
This work proposes a family of symmetric multi-player alignment games and proves that any symmetric Nash equilibrium policy of the $(k+1)-player alignment game achieves the optimal $(k,\frac{k}{k+1})$-robust alignment.
Yang Cai, Weiqiang Zheng· arXiv.org· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes an approach that recasts the task as automated knowledge base construction: prompting an LLM to synthesize a 3NF-compliant relational schema from Wikipedia infobox timelines, populating the schema to obtain a queryable database, and generating and executing SQL queries against it, with QA accuracy se...
In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by separating events that happened at different times, this work probes the ability...
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini et al.· 0 citations
A novel threat is unveiled in which attackers steer the RAG system's response by injecting malicious passages into its knowledge base, enabling the attacker to steer the response without altering the user input or modifying the RAG weights.
Jiaqi Xue, Meng Zheng, Yebowen Hu et al.· arXiv.org· 109 citations· ⚡8
The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems, covering the full stack from first principles to production deployment. The central thesis: building great agentic systems requires understanding every layer of the pipeline, not just one. The book opens...
This work identifies the first token of the response as a structurally distinct target for diversification, largely overlooked in prior work, and finds that the first-token distribution is sharply concentrated and only weakly related to downstream correctness, as lower-probability candidates can yield similarly accurat...
This paper systematically investigates two principal test-time scaling axes of LLM agents: sequential scaling through extended interaction and parallel scaling through trajectory sampling, and finds that neither scaling axis can consistently yield meaningful gains from additional test-time compute in realistic environm...
Xiao-Chuan Li, Ryan Ming, P. Setlur et al.· 23 citations· ⚡1
STEPQuant is proposed, a spatial-temporal post-training quantization framework for Delta-rule recurrent states that allocates precision according to error magnitude and memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error.
Bing-Chen Yao, Hao-Bo Xu, Hao-Kun Lin et al.· 0 citations
GEB is introduced, a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment and demonstrating improvements over prior memory frameworks in both multiple-choice and open-ended question answ...
Hui-Hui Ren, Lei Fan, Henry Pao et al.· 0 citations
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.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
