MLINFO COLLECTION
少数試行で条件探索を進めるベイズ最適化、実験計画、ブラックボックス最適化を扱います。
Game theory identifies when a strategic action should be accepted, but not how long a live, language-based counterpart will continue to accept it. We entered the GLEE competition in its final week…
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial…
We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed decision together with a confidence score estimating the…
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training…
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of…
Tasks such as quadrotor dynamic-gate racing require agents to anticipate external motion while maintaining precise high-frequency control. World-model-based reinforcement learning provides a natural…
On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Self-distillation further removes the need for an external teacher by using the…
\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and…
Understanding catastrophic forgetting, in which learning new tasks degrades performance on previously learned tasks, remains a fundamental challenge in continual learning (CL). Existing theoretical…
Apple Silicon is among the most widely used platforms for local LLM inference, yet nearly all inference optimizations are designed and validated on server-class NVIDIA GPUs under batched serving…
Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training…
Probabilistic computing has proved useful for combinatorial optimization, but conventional implementations rely on binary stochastic units and sigmoid-based updates. Extending these systems to…
Finite element model updating is among the most general approaches to discover constitutive models from structural experiments: since the displacement field is computed rather than measured, it…
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer.…
Reinforcement learning has emerged as an effective approach for combinatorial optimization, but most existing methods focus on problems such as the Travelling Salesperson Problem (TSP) in which all…
Reward models score responses for preference optimization, filtering and ranking, and pooling scores across prompts needs them to be comparable. Yet pairwise evaluation compares two responses to the…
Large language models (LLMs) have demonstrated strong potential to automate heuristic design for NP-hard combinatorial optimization (CO) tasks without human intervention. Recent methods predominantly…
While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-time interventions, but…
Existing agricultural advisories to farmers suffer from several limitations: (a) remain largely expert-driven, (b) do not adequately account for in-season weather, and (c) do not scale to individual…
Offline contextual pricing often relies on logged observational data, but faces challenges from distributional shifts between training and deployment environments. Distributionally robust…
General-purpose embeddings trained on profile similarity often misrank candidates in professional networks, where relevance is inherently complementary rather than symmetric. For example, job seekers…
Just as different languages express the same concept through different words, neural networks express similar functions through incompatible coordinate systems. Different architectures, random…
The security of modern public-key cryptographic systems, such as RSA, Diffie-Hellman, and ECC, depends entirely on the computational intractability of the integer factorization and discrete logarithm…
With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction. LLM-based agents are therefore increasingly used to tackle complex long-horizon…